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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    猇
    -0.08
    膙
    -0.07
    arti
    -0.07
    眼袋
    -0.06
    玙
    -0.06
     buflen
    -0.06
    厚度
    -0.06
    _COMPARE
    -0.06
    _WAIT
    -0.06
    薇
    -0.06
    POSITIVE LOGITS
     disco
    0.08
     Samp
    0.08
     empowerment
    0.07
    还
    0.07
    使得
    0.07
    贾
    0.07
     =======
    0.07
     Billing
    0.07
    umba
    0.07
    solution
    0.07
    Act Density 0.005%

    No Known Activations