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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hedge
    -0.07
     days
    -0.06
     Ampl
    -0.06
     typography
    -0.06
    数组
    -0.06
    .sequence
    -0.06
    _WALL
    -0.06
    >G
    -0.06
    вами
    -0.06
     μ
    -0.06
    POSITIVE LOGITS
    ание
    0.07
     Grain
    0.07
     naší
    0.06
    hack
    0.06
    lerde
    0.06
    ighter
    0.06
    wand
    0.06
    luğu
    0.06
    ?=
    0.06
     inflater
    0.06
    Act Density 0.000%

    No Known Activations