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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sw
    -0.08
    Work
    -0.07
     accounted
    -0.07
     register
    -0.07
    信
    -0.07
     �
    -0.07
     replies
    -0.06
    _PS
    -0.06
    ης
    -0.06
     COS
    -0.06
    POSITIVE LOGITS
    bove
    0.07
    標
    0.07
    Desde
    0.06
    prene
    0.06
     ofere
    0.06
     عاما
    0.06
    ंर
    0.06
    "])){↵
    0.06
    payments
    0.06
    stract
    0.06
    Act Density 0.000%

    No Known Activations