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

    Neuronpedia

    INDEX
    Explanations

    narrowing down possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abuses
    0.45
     STAN
    0.45
     დღ
    0.42
     refunds
    0.42
     reservations
    0.41
    STAN
    0.41
     abused
    0.40
     allocates
    0.40
     allocating
    0.39
     운영
    0.39
    POSITIVE LOGITS
     narrowed
    0.98
     candidate
    0.84
     narrowing
    0.84
    候補
    0.82
     후보
    0.80
     candidates
    0.80
     possibilities
    0.80
     narrows
    0.80
    候选
    0.79
    candidate
    0.77
    Act Density 0.141%

    No Known Activations