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

    Neuronpedia

    INDEX
    Explanations

    ungal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .available
    -0.07
     utterly
    -0.06
    .attrs
    -0.06
     })).
    -0.06
    ,alpha
    -0.06
     schw
    -0.06
     sigmoid
    -0.06
     권
    -0.06
    trigger
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    (actor
    0.07
    ungalow
    0.07
     AGRE
    0.07
    ución
    0.07
     Χ
    0.06
    년
    0.06
    >About
    0.06
    αλλ
    0.06
     /(
    0.06
    Faces
    0.06
    Act Density 0.004%

    No Known Activations