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

    Neuronpedia

    INDEX
    Explanations

    words related to data processing and manipulation in a structured format

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

    Text within XML-like tags

    np_acts-logits-general · gemini-2.0-flash

    delim followed by angle brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lawson
    -0.53
    __()
    -0.51
    ival
    -0.50
     gas
    -0.50
    Isolation
    -0.48
    ayo
    -0.47
     isolation
    -0.47
     Ress
    -0.47
     mil
    -0.46
     Hess
    -0.45
    POSITIVE LOGITS
     <
    1.02
    <
    0.94
     $<
    0.82
    tvguidetime
    0.80
     '<
    0.77
     $<$
    0.77
    "><
    0.75
     `<
    0.75
     "<
    0.73
     utafitiHapana
    0.73
    Act Density 0.164%

    No Known Activations