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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hap
    -0.07
    ({},
    -0.06
    umba
    -0.06
     trophy
    -0.06
    bable
    -0.06
     dět
    -0.06
    >')↵
    -0.06
    pect
    -0.06
     tác
    -0.06
    思考
    -0.06
    POSITIVE LOGITS
    (od
    0.07
    сті
    0.06
    _visibility
    0.06
    �
    0.06
     incarceration
    0.06
     -*-↵↵
    0.06
    eda
    0.06
    //===
    0.06
     customers
    0.06
    (timer
    0.06
    Act Density 0.000%

    No Known Activations