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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отд
    -0.07
    Damage
    -0.07
     elimination
    -0.07
    ore
    -0.07
     Vương
    -0.07
     harmonic
    -0.07
    紅
    -0.06
    /functions
    -0.06
    /hooks
    -0.06
     Bard
    -0.06
    POSITIVE LOGITS
    ayscale
    0.07
    ázky
    0.06
     reserv
    0.06
     }*/↵↵
    0.06
     Subjects
    0.06
    ियर
    0.06
    .$
    0.06
     Spanish
    0.06
    >Action
    0.06
     becomes
    0.06
    Act Density 0.037%

    No Known Activations