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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Allowed
    -0.07
     rhs
    -0.07
    ChangeListener
    -0.06
     nhau
    -0.06
     सब
    -0.06
    wanted
    -0.06
    Beautiful
    -0.06
    Unlike
    -0.06
    oscopic
    -0.06
    Jer
    -0.06
    POSITIVE LOGITS
    ："+
    0.07
    솔
    0.06
    (Render
    0.06
    _ING
    0.06
     danske
    0.06
     doldur
    0.06
    find
    0.06
     reinc
    0.06
    .Should
    0.06
    Ph
    0.06
    Act Density 0.095%

    No Known Activations