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

    Neuronpedia

    INDEX
    Explanations

    `/b` switch with `windows`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chihuahua
    0.48
     Ouvrard
    0.46
     nDims
    0.43
     Dun
    0.43
     Hera
    0.43
     کوچ
    0.42
     レッド
    0.42
     Richie
    0.42
     Hara
    0.42
     जीनत
    0.41
    POSITIVE LOGITS
    TYPES
    0.45
     types
    0.38
    Types
    0.38
     undoubt
    0.38
     типо
    0.37
    suppliers
    0.36
    Causes
    0.35
     '
    0.34
    कल
    0.34
    types
    0.34
    Act Density 0.000%

    No Known Activations