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

    Neuronpedia

    INDEX
    Explanations

    inner child, inner dialogue, inner self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     распростра
    0.41
     visually
    0.41
     financially
    0.41
     చేసిన
    0.40
    ố
    0.40
     относи
    0.40
    ogne
    0.40
    minify
    0.40
     economies
    0.39
    oners
    0.39
    POSITIVE LOGITS
     inner
    0.91
     dormant
    0.87
     instincts
    0.85
     wewnętr
    0.82
    Inner
    0.79
     внутреннего
    0.77
     внутріш
    0.77
     Inner
    0.75
     latent
    0.75
     subconscious
    0.74
    Act Density 0.028%

    No Known Activations