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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Allows
    -0.07
     навіть
    -0.07
    lld
    -0.06
    来た
    -0.06
    -port
    -0.06
     بدون
    -0.06
    不可
    -0.06
    berries
    -0.06
     Frames
    -0.06
     Silk
    -0.06
    POSITIVE LOGITS
    Hi
    0.06
    صد
    0.06
    .API
    0.06
    utc
    0.06
     Extract
    0.06
    .Rest
    0.06
    ajs
    0.06
    _signal
    0.06
    uo
    0.06
    anness
    0.06
    Act Density 0.000%

    No Known Activations