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

    Neuronpedia

    INDEX
    Explanations

    qualifying or limiting descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Captain
    0.48
     சேர்க்க
    0.41
    েদ
    0.41
    沘
    0.41
    erà
    0.40
    July
    0.39
     Edw
    0.39
    ર
    0.39
    ErrorMessage
    0.39
    λό
    0.39
    POSITIVE LOGITS
     inadequate
    0.43
     exces
    0.41
     insufficient
    0.41
     thefts
    0.40
     excessive
    0.40
     conducive
    0.40
     pooled
    0.38
     Theft
    0.38
     karet
    0.38
     proofs
    0.38
    Act Density 0.000%

    No Known Activations