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

    Neuronpedia

    INDEX
    Explanations

    java import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iversary
    0.91
    дык
    0.89
    agena
    0.82
    Acid
    0.80
    renzia
    0.79
    izieren
    0.79
    തിന്
    0.77
    嫄
    0.77
    katore
    0.77
    чную
    0.76
    POSITIVE LOGITS
     javafx
    0.75
     kom
    0.71
     google
    0.69
     Google
    0.68
     neo
    0.68
     jes
    0.67
    junit
    0.67
     influenza
    0.65
    google
    0.64
     latter
    0.63
    Act Density 0.007%

    No Known Activations