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

    Neuronpedia

    INDEX
    Explanations

    online calculators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anes
    0.43
     Math
    0.42
     Checking
    0.41
     rab
    0.41
    使用
    0.40
     Linda
    0.40
    čení
    0.40
     math
    0.39
     Susan
    0.39
     matemat
    0.39
    POSITIVE LOGITS
     ambiguity
    0.65
     ambiguous
    0.63
     disamb
    0.63
    disamb
    0.55
     ambiguities
    0.55
     ambigu
    0.52
    暧
    0.45
     unambiguous
    0.44
     unambiguously
    0.44
     अंब
    0.43
    Act Density 0.001%

    No Known Activations