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

    Neuronpedia

    INDEX
    Explanations

    references to numbers or numerical data

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

    Tokens immediately following commas

    np_acts-logits-general · gemini-2.0-flash

    comma followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nachdem
    -0.56
    waitKey
    -0.51
    toHave
    -0.51
    ModelSerializer
    -0.49
    本次
    -0.47
    Loves
    -0.47
    Péri
    -0.47
    posedge
    -0.47
     propose
    -0.46
     RSSSF
    -0.46
    POSITIVE LOGITS
    0.69
     automaticamente
    0.65
     становника
    0.65
     denkt
    0.62
     denken
    0.62
     immediately
    0.60
     it
    0.60
     instinctively
    0.60
    uxxxx
    0.59
     שוליים
    0.58
    Act Density 0.253%

    No Known Activations