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

    Neuronpedia

    INDEX
    Explanations

    lists followed by for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ãĤ
    -0.09
    434
    -0.09
    ovo
    -0.08
    oeff
    -0.08
     nip
    -0.08
    ava
    -0.08
     Frid
    -0.08
    otive
    -0.07
     forfe
    -0.07
     haf
    -0.07
    POSITIVE LOGITS
     for
    0.11
    ):\n
    0.10
    âĨĵ
    0.10
    ":\n
    0.10
     длÑı
    0.10
    ):\n\n
    0.10
     könnte
    0.10
    ]:\n\n
    0.10
    )):\n
    0.10
    "):\n
    0.09
    Act Density 0.197%

    No Known Activations