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

    Neuronpedia

    INDEX
    Explanations

    mentions of variable values in code

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

    "value" and variants

    np_acts-logits-general · gemini-2.0-flash

    value: or "value"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    st
    -0.51
    <h1>
    -0.51
    9
    -0.48
    <
    -0.47
    nd
    -0.46
     Humphreys
    -0.46
     Grims
    -0.45
     Schrö
    -0.45
    3
    -0.45
    not
    -0.45
    POSITIVE LOGITS
     Value
    1.19
     VALUE
    1.13
     value
    1.08
    Value
    1.07
    value
    1.01
     getValue
    0.98
    VALUE
    0.97
     Values
    0.96
    ValueStyle
    0.95
     valu
    0.91
    Act Density 0.163%

    No Known Activations