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

    Neuronpedia

    INDEX
    Explanations

    ll

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    付け
    -0.08
    不小心
    -0.08
    -pound
    -0.07
    ellaneous
    -0.07
    .Socket
    -0.07
    utor
    -0.07
     fec
    -0.07
    午
    -0.07
    hoc
    -0.07
    limitations
    -0.07
    POSITIVE LOGITS
     Motorola
    0.08
    מקד
    0.07
     &)
    0.07
    .charAt
    0.07
    &);↵
    0.07
    Abort
    0.07
    _restrict
    0.07
    GL
    0.06
    _cmos
    0.06
    Coeff
    0.06
    Act Density 0.004%

    No Known Activations