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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    labus
    -0.79
    aragus
    -0.77
    UnknownFieldSet
    -0.76
    structors
    -0.75
     Starling
    -0.72
    thâu
    -0.71
    nologue
    -0.71
     saliva
    -0.69
     Ancestry
    -0.69
     RISERV
    -0.68
    POSITIVE LOGITS
    ated
    0.54
    ित
    0.54
    IsContent
    0.53
    lich
    0.52
    est
    0.50
    ish
    0.49
    ory
    0.48
    止
    0.48
    ap
    0.47
    Copyright
    0.47
    Act Density 0.065%

    No Known Activations