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

    Neuronpedia

    INDEX
    Explanations

    Integer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aggregate
    -0.07
     amt
    -0.07
    Park
    -0.07
     Ry
    -0.07
     responsibility
    -0.06
     Slate
    -0.06
     contribution
    -0.06
     tịch
    -0.06
     relationship
    -0.06
     presidente
    -0.06
    POSITIVE LOGITS
     اجرای
    0.07
     heav
    0.06
     komen
    0.06
    openssl
    0.06
     clazz
    0.06
    цять
    0.06
    leanup
    0.06
     NSLayoutConstraint
    0.06
    ồi
    0.06
    /set
    0.06
    Act Density 0.007%

    No Known Activations