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

    Neuronpedia

    INDEX
    Explanations

    pseudo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     story
    -0.06
     notoriously
    -0.06
     ropes
    -0.06
    JNIEnv
    -0.06
    destroy
    -0.06
    oại
    -0.06
     NOR
    -0.06
    няют
    -0.06
     Tony
    -0.06
     cloth
    -0.06
    POSITIVE LOGITS
     ذات
    0.07
     breve
    0.06
    _ec
    0.06
     {}↵↵↵
    0.06
    обще
    0.06
     пап
    0.06
    識
    0.06
    .NO
    0.06
    (bus
    0.06
     ση
    0.06
    Act Density 0.003%

    No Known Activations