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

    Neuronpedia

    INDEX
    Explanations

    details database

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (((
    -0.06
    كور
    -0.06
    olation
    -0.06
    049
    -0.06
     で
    -0.06
     revenge
    -0.06
    fortunate
    -0.06
     score
    -0.06
    ามารถ
    -0.06
    unts
    -0.06
    POSITIVE LOGITS
     newVal
    0.06
     و
    0.06
     bibli
    0.06
    */↵
    0.06
     fascism
    0.06
     ;
↵
    0.06
     codigo
    0.06
     )
    0.06
    ...↵
    0.06
    .substring
    0.06
    Act Density 0.000%

    No Known Activations