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

    Neuronpedia

    INDEX
    Explanations

    Scientific/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Merkel
    -0.08
    Factory
    -0.07
    肌
    -0.07
    	Update
    -0.07
    �
    -0.06
     Zuckerberg
    -0.06
     cages
    -0.06
    acker
    -0.06
     Це
    -0.06
     khuẩn
    -0.06
    POSITIVE LOGITS
    ynı
    0.07
     громадян
    0.06
     xrange
    0.06
    >'
    0.06
    range
    0.06
    apollo
    0.06
    .reset
    0.06
     пы
    0.06
    .keyboard
    0.06
    uz
    0.06
    Act Density 0.039%

    No Known Activations