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

    Neuronpedia

    INDEX
    Explanations

    matplotlib plotting code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ویل
    -0.07
    °
    -0.07
     rsp
    -0.07
     třeba
    -0.06
    获
    -0.06
    riet
    -0.06
     minecraft
    -0.06
    _interp
    -0.06
    combination
    -0.06
    }>{
    -0.06
    POSITIVE LOGITS
     attendee
    0.07
     Sinn
    0.06
     Dummy
    0.06
    Angle
    0.06
     �
    0.06
    Social
    0.06
     Gad
    0.06
    κης
    0.06
    _ber
    0.06
    ۱۳۹
    0.06
    Act Density 0.026%

    No Known Activations