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

    Neuronpedia

    INDEX
    Explanations

    lesson plans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ีช
    -0.07
     Loans
    -0.06
     Kurum
    -0.06
    τικός
    -0.06
    行政
    -0.06
     oficial
    -0.06
     IOCTL
    -0.06
    ичес
    -0.06
    _rgb
    -0.06
     jewish
    -0.06
    POSITIVE LOGITS
     challenger
    0.07
    ğer
    0.06
     På
    0.06
    Implemented
    0.06
    [K
    0.06
    _lift
    0.06
     σχε
    0.06
     narration
    0.06
     narrowing
    0.06
     görev
    0.06
    Act Density 0.067%

    No Known Activations