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

    Neuronpedia

    INDEX
    Explanations

    Numbers and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ancouver
    -0.06
     crew
    -0.06
     Fighters
    -0.06
     kvinne
    -0.06
     toàn
    -0.06
    hx
    -0.06
     Kaw
    -0.06
    ��
    -0.06
     formerly
    -0.06
    ávě
    -0.05
    POSITIVE LOGITS
    exemple
    0.06
    .bold
    0.06
     NUIT
    0.06
    _ADAPTER
    0.06
    unctuation
    0.06
     dividends
    0.06
    (rs
    0.06
     Demo
    0.06
     راست
    0.06
     moving
    0.06
    Act Density 0.010%

    No Known Activations