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

    Neuronpedia

    INDEX
    Explanations

    hal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    874
    -0.07
    353
    -0.06
    340
    -0.06
    ε
    -0.06
    057
    -0.06
     BLUE
    -0.06
    546
    -0.06
    347
    -0.06
    350
    -0.06
     expiry
    -0.06
    POSITIVE LOGITS
     их
    0.06
     overlays
    0.06
    azioni
    0.06
     Calcul
    0.06
     handbook
    0.06
    attr
    0.06
    andra
    0.06
    ishops
    0.06
    услов
    0.06
    imen
    0.06
    Act Density 0.766%

    No Known Activations