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

    Neuronpedia

    INDEX
    Explanations

    identifiers followed by underscore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     socalled
    0.50
    <unused395>
    0.43
     (‘
    0.42
    ോദ
    0.41
    ！」
    0.40
    𒇻
    0.38
    搂
    0.37
    റ്റ്‌
    0.37
     («
    0.37
     outrageous
    0.36
    POSITIVE LOGITS
    _
    1.12
    -
    0.90
    ・
    0.79
    \_
    0.76
    _{
    0.59
    _${
    0.49
    ‐
    0.46
    ־
    0.46
    0.46
    -_-
    0.44
    Act Density 0.043%

    No Known Activations