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

    Neuronpedia

    INDEX
    Explanations

    not alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഇപ്പോ
    0.65
     Yes
    0.63
    क्की
    0.61
     institucional
    0.60
     ?>"
    0.59
    元素
    0.58
     yes
    0.56
    Yes
    0.56
     காணப்படும்
    0.55
     elementos
    0.54
    POSITIVE LOGITS
     evaluations
    0.92
     worth
    0.87
     평가
    0.85
    valu
    0.85
     Worth
    0.85
    Evalu
    0.84
     value
    0.84
     amusing
    0.82
     Value
    0.82
     evaluating
    0.81
    Act Density 0.244%

    No Known Activations