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

    Neuronpedia

    INDEX
    Explanations

    Visual Studio Code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stown
    0.93
     descoberta
    0.90
     sobretudo
    0.86
    ены
    0.85
     скорее
    0.84
     capazes
    0.84
     provavelmente
    0.83
     maneiras
    0.83
    oader
    0.82
    ный
    0.82
    POSITIVE LOGITS
    Clear
    0.82
    tu
    0.77
    t
    0.77
    success
    0.74
    פ
    0.74
    Ginger
    0.73
    ג
    0.73
    Case
    0.72
     plă
    0.71
     Thyroid
    0.71
    Act Density 0.002%

    No Known Activations