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

    Neuronpedia

    INDEX
    Explanations

    JavaScript-related commands and syntax

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

    Code-related tokens and symbols

    np_acts-logits-general · gemini-2.0-flash

    view in views/ register

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.60
    PerformLayout
    -0.55
    thâu
    -0.55
    moiselle
    -0.54
    \{\\
    -0.54
    الدراسه
    -0.53
     становника
    -0.53
    ✨:
    -0.53
    UnknownFieldSet
    -0.52
    ̍t
    -0.50
    POSITIVE LOGITS
    use
    0.66
    all
    0.52
    (['/
    0.51
     use
    0.51
     bis
    0.48
    ReusableCell
    0.48
    param
    0.48
    ENAS
    0.47
     Maro
    0.47
    isant
    0.46
    Act Density 0.101%

    No Known Activations