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
     conservatism
    -0.06
    aupt
    -0.06
    的是
    -0.06
     Su
    -0.06
     surpass
    -0.06
    Spy
    -0.06
    ंक
    -0.06
     Roland
    -0.06
     Activation
    -0.06
    であ
    -0.06
    POSITIVE LOGITS
     테
    0.07
    Subviews
    0.06
    ============
    0.06
    ughs
    0.06
    ैं,
    0.06
    assadors
    0.06
    .AttributeSet
    0.06
     ölüm
    0.06
    γι
    0.06
    (MouseEvent
    0.06
    Act Density 0.000%

    No Known Activations