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

    Neuronpedia

    INDEX
    Explanations

    fulfill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    threat
    -0.07
    /xml
    -0.07
    Reset
    -0.07
    ーの
    -0.06
    保护
    -0.06
    054
    -0.06
    Prop
    -0.06
     Solution
    -0.06
    _oct
    -0.06
    Operation
    -0.06
    POSITIVE LOGITS
    aleza
    0.07
     çalışmalar
    0.07
     rewarding
    0.06
     aktuální
    0.06
     radiant
    0.06
     thất
    0.06
    _expected
    0.06
     inplace
    0.06
    uala
    0.06
    (branch
    0.06
    Act Density 0.010%

    No Known Activations