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

    Neuronpedia

    INDEX
    Explanations

    gain perspective and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ْم
    0.52
    of
    0.46
    ms
    0.46
    ing
    0.45
    ford
    0.44
    ulating
    0.44
    ching
    0.44
     відбу
    0.44
    чём
    0.44
    즈
    0.44
    POSITIVE LOGITS
     Wessex
    0.46
     nü
    0.44
     factorización
    0.44
     Removal
    0.43
     asociada
    0.43
    ሃኒ
    0.43
     ENO
    0.42
     mandarin
    0.42
     manžel
    0.42
     Serving
    0.42
    Act Density 0.004%

    No Known Activations