Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    elements related to collaboration and collective efforts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    dollar amounts and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    herjee
    -0.54
     estekak
    -0.51
    tagHelperRunner
    -0.47
    кож
    -0.47
     zobac
    -0.46
    違います
    -0.46
    rapeau
    -0.45
    навли
    -0.45
     کیلومتر
    -0.45
    oprecip
    -0.45
    POSITIVE LOGITS
     Altogether
    0.97
     resulting
    0.93
    resulting
    0.91
     resultant
    0.84
     Together
    0.83
     ergibt
    0.82
     Result
    0.80
     ergeben
    0.79
    Together
    0.79
     получается
    0.76
    Act Density 0.727%

    No Known Activations