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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cascade
    -0.06
    acial
    -0.06
     page
    -0.06
     vit
    -0.06
    department
    -0.06
    ULATOR
    -0.06
    Exec
    -0.06
     summer
    -0.06
    ↵        ↵
    -0.06
    xico
    -0.06
    POSITIVE LOGITS
    tuğ
    0.07
     растений
    0.06
    شنامه
    0.06
    ุงเทพ
    0.06
     SCI
    0.06
    ，《
    0.06
    uale
    0.06
    .Experimental
    0.06
    +='
    0.06
     looph
    0.06
    Act Density 0.096%

    No Known Activations