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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aden
    -0.07
     bowel
    -0.07
    달
    -0.07
     avid
    -0.06
    argin
    -0.06
    rika
    -0.06
     nave
    -0.06
     Lantern
    -0.06
     resistant
    -0.06
    省
    -0.06
    POSITIVE LOGITS
    ownership
    0.07
    _BL
    0.06
     برگزار
    0.06
     συμπ
    0.06
    ニック
    0.06
    .password
    0.06
    .single
    0.06
     MST
    0.06
    _RUN
    0.06
    culator
    0.06
    Act Density 0.016%

    No Known Activations