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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dh
    -0.07
     Xml
    -0.06
    aked
    -0.06
    cdf
    -0.06
     Δ
    -0.06
    <dynamic
    -0.06
    bsolute
    -0.06
    zz
    -0.06
    ArrayList
    -0.06
    .parseInt
    -0.06
    POSITIVE LOGITS
     norsk
    0.07
     tenure
    0.07
     par
    0.07
     ON
    0.07
     Seriously
    0.07
    /es
    0.07
     colors
    0.06
     типа
    0.06
     bust
    0.06
     nied
    0.06
    Act Density 0.029%

    No Known Activations