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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     titleLabel
    -0.07
     ayr
    -0.07
     billeder
    -0.07
    _vue
    -0.07
     рекомен
    -0.07
     republika
    -0.06
     fich
    -0.06
     će
    -0.06
     intervened
    -0.06
     povin
    -0.06
    POSITIVE LOGITS
     glowing
    0.14
     stash
    0.08
    imax
    0.07
     Gary
    0.07
     Queens
    0.06
     Drain
    0.06
     Mount
    0.06
     harness
    0.06
     gauge
    0.06
     Hidden
    0.06
    Act Density 0.002%

    No Known Activations