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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adress
    -0.08
     sen
    -0.07
     sarc
    -0.07
     Meter
    -0.06
    likle
    -0.06
     Produkt
    -0.06
     clicked
    -0.06
    ٥
    -0.06
     IPAddress
    -0.06
    üp
    -0.06
    POSITIVE LOGITS
    _unref
    0.07
     }}/
    0.06
     ボ
    0.06
     ;↵↵
    0.06
    pga
    0.06
    ovy
    0.06
    oklyn
    0.06
    /fonts
    0.06
     erotiske
    0.06
    ubber
    0.06
    Act Density 0.260%

    No Known Activations