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

    Neuronpedia

    INDEX
    Explanations

    Code diffs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assertTrue
    -0.06
    (""
    -0.06
    �
    -0.06
     itemName
    -0.06
    .radio
    -0.06
    ��
    -0.06
    .super
    -0.06
    ていない
    -0.05
    ЎыџNЎыџN
    -0.05
     hài
    -0.05
    POSITIVE LOGITS
    Total
    0.08
     Calculate
    0.08
    �
    0.07
     محصولات
    0.07
    much
    0.07
     eher
    0.07
     utter
    0.07
     Total
    0.07
     Computes
    0.07
     instruct
    0.06
    Act Density 0.001%

    No Known Activations