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

    Neuronpedia

    INDEX
    Explanations

    general english text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     цель
    -0.06
    _LOG
    -0.06
     Floors
    -0.06
     riders
    -0.06
    -t
    -0.06
     Cres
    -0.06
     yahoo
    -0.06
    Toe
    -0.06
     fronts
    -0.06
     aston
    -0.06
    POSITIVE LOGITS
     Invitation
    0.07
     iPad
    0.07
     электр
    0.07
    具体
    0.06
    isLoading
    0.06
    predicate
    0.06
    okino
    0.06
    ansi
    0.06
     due
    0.06
    .nz
    0.06
    Act Density 0.000%

    No Known Activations