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

    Neuronpedia

    INDEX
    Explanations

    +/-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Classification
    -0.07
     Acad
    -0.07
     площ
    -0.06
     assemblies
    -0.06
     Commod
    -0.06
     Labour
    -0.06
    am
    -0.06
    ad
    -0.06
     barcode
    -0.06
     流
    -0.06
    POSITIVE LOGITS
     +/-
    0.07
     lesbi
    0.07
     alpha
    0.07
    _CRYPTO
    0.07
     UN
    0.07
    Alpha
    0.07
     vyz
    0.07
    фер
    0.07
    NOTE
    0.07
    _AHB
    0.07
    Act Density 0.005%

    No Known Activations