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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    á
    -0.07
    arma
    -0.07
    IFT
    -0.07
    .ba
    -0.06
     improperly
    -0.06
    adal
    -0.06
    lc
    -0.06
    єв
    -0.06
    ('=
    -0.06
    oğlu
    -0.06
    POSITIVE LOGITS
     '"';↵
    0.06
     altro
    0.06
    ;">
↵
    0.06
    ٬
    0.06
    :{
↵
    0.06
     финансов
    0.05
    URITY
    0.05
     :]↵
    0.05
    }],↵
    0.05
    )){↵↵
    0.05
    Act Density 0.039%

    No Known Activations