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

    Neuronpedia

    INDEX
    Explanations

    the word "and" in math problems

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.86
    principalTable
    -0.70
    DebuggerNonUser
    -0.65
    lapsingToolbar
    -0.63
    PYX
    -0.63
     فريبيس
    -0.62
     مشين
    -0.60
    RefNanny
    -0.59
    oneofs
    -0.56
    PathParam
    -0.56
    POSITIVE LOGITS
    <bos>
    0.74
     fallu
    0.56
    География
    0.54
    ggiamento
    0.54
     Locals
    0.53
     coronation
    0.52
    Locals
    0.52
     Sedan
    0.50
     voulons
    0.50
     Metacritic
    0.49
    Act Density 0.011%

    No Known Activations