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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arak
    -0.07
    $temp
    -0.07
    -title
    -0.07
     дисцип
    -0.07
    lament
    -0.06
    -control
    -0.06
     heure
    -0.06
    -normal
    -0.06
    ilmek
    -0.06
    数组
    -0.06
    POSITIVE LOGITS
     ділян
    0.07
    astics
    0.06
    運
    0.06
    ederal
    0.06
    _PATCH
    0.06
     calf
    0.06
    /St
    0.06
    協
    0.06
     DevExpress
    0.06
    outu
    0.05
    Act Density 0.001%

    No Known Activations