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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cryptoc
    -0.07
     OBS
    -0.07
    ’h
    -0.07
    'h
    -0.07
     franch
    -0.06
    �
    -0.06
     lineback
    -0.06
     porr
    -0.06
     pa
    -0.06
     спів
    -0.06
    POSITIVE LOGITS
    邊
    0.06
    !(↵
    0.06
    블
    0.06
    yı
    0.06
     Available
    0.06
    /{{
    0.06
     SUS
    0.06
    *****/↵
    0.06
     booze
    0.06
    ileceğini
    0.06
    Act Density 0.002%

    No Known Activations