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

    Neuronpedia

    INDEX
    Explanations

    key qualities and considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    أ
    1.02
    ї
    1.01
    ح
    0.95
    pthread
    0.91
     또는
    0.90
    または
    0.90
    즉
    0.90
    jax
    0.89
    etically
    0.88
     nama
    0.87
    POSITIVE LOGITS
     सराह
    1.12
     alleviate
    1.05
     diminish
    1.04
    ;.
    1.01
     également
    1.00
    0
    0.98
     diminishes
    0.97
    .}
    0.97
     spares
    0.97
     pondering
    0.97
    Act Density 0.611%

    No Known Activations