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

    Neuronpedia

    INDEX
    Explanations

    nouns related to amounts of time, money, or measurements of physical interaction.

    oai_token-act-pair · gemini-2.0-flash

    Time and small amounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     பே
    -0.53
     Weller
    -0.51
    批量
    -0.51
     שול
    -0.50
     few
    -0.48
     town
    -0.48
    Replacement
    -0.48
     volo
    -0.47
    rboles
    -0.47
    landa
    -0.47
    POSITIVE LOGITS
    aarrggbb
    0.86
    DebuggerNonUser
    0.82
    OGND
    0.77
     invokingState
    0.68
     NgModule
    0.64
    <bos>
    0.63
    NameInMap
    0.62
     Numerade
    0.60
    #
    0.59
     '\\;'
    0.58
    Act Density 2.022%

    No Known Activations