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

    Neuronpedia

    INDEX
    Explanations

    so that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     name
    0.84
     slang
    0.83
     joke
    0.79
     some
    0.76
     vodka
    0.76
     nasal
    0.74
     algunas
    0.73
     seems
    0.73
     username
    0.73
     typo
    0.73
    POSITIVE LOGITS
    从而
    1.07
    enhance
    1.05
     mejorar
    1.04
     Ultimately
    1.03
     предотвра
    1.02
     migliorare
    1.02
    improve
    1.02
     enhance
    1.01
     ultimately
    0.98
    Ultimately
    0.98
    Act Density 0.001%

    No Known Activations