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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิล
    -0.07
    �
    -0.07
    lications
    -0.07
     Yoga
    -0.06
     Tears
    -0.06
     Colts
    -0.06
    abor
    -0.06
     GOD
    -0.06
    اون
    -0.06
    erif
    -0.06
    POSITIVE LOGITS
    "=>"
    0.07
     financ
    0.07
     etc
    0.07
    getDoctrine
    0.07
    $this
    0.06
     remar
    0.06
     ویژ
    0.06
    ivable
    0.06
    .Inv
    0.06
    _subplot
    0.06
    Act Density 0.031%

    No Known Activations