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

    Neuronpedia

    INDEX
    Explanations

    power and electricity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    听着
    -0.08
     poco
    -0.08
    '].'/
    -0.07
     occupy
    -0.07
     Ninth
    -0.07
     evacuate
    -0.07
     الجامعة
    -0.07
     localize
    -0.06
     forthcoming
    -0.06
     oc
    -0.06
    POSITIVE LOGITS
     scaling
    0.08
     Faith
    0.07
    ⴹ
    0.07
    מנהל
    0.07
     ============================================================================↵
    0.07
    رسم
    0.07
     Gaga
    0.07
    пром
    0.07
    arna
    0.07
    _HANDLE
    0.07
    Act Density 0.028%

    No Known Activations