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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NSMutable
    -0.07
    ucch
    -0.06
     hatten
    -0.06
    comfort
    -0.06
     Ör
    -0.06
    Comfort
    -0.06
    _consumer
    -0.06
    strncmp
    -0.06
     видно
    -0.06
     sagt
    -0.06
    POSITIVE LOGITS
     Tomorrow
    0.07
     permanent
    0.07
     OnInit
    0.06
    //[
    0.06
    entions
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     маз
    0.06
    essel
    0.06
    iterator
    0.06
    riday
    0.06
    Act Density 0.030%

    No Known Activations