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

    Neuronpedia

    INDEX
    Explanations

    focus emphasis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Layout
    -0.09
    ाफ
    -0.07
    Curr
    -0.06
    ^(
    -0.06
     harassed
    -0.06
     Tool
    -0.06
     Seven
    -0.06
    William
    -0.06
    ildren
    -0.06
    /ex
    -0.06
    POSITIVE LOGITS
    .ravel
    0.07
     تیم
    0.07
     часа
    0.07
     BN
    0.06
     funcion
    0.06
     bệnh
    0.06
     شروع
    0.06
     risult
    0.06
     tavsiye
    0.06
    -calendar
    0.06
    Act Density 0.014%

    No Known Activations