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

    Neuronpedia

    INDEX
    Explanations

    action verbs and strong nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exponential
    0.56
     dimensionality
    0.54
     dynamism
    0.51
     transformations
    0.51
     paradox
    0.50
     randomness
    0.50
     dystopian
    0.50
     misalignment
    0.50
     absurdity
    0.50
     decomposition
    0.49
    POSITIVE LOGITS
     promptly
    0.50
     voluntarily
    0.45
     commencent
    0.45
     oversee
    0.45
    写真を
    0.45
     notify
    0.44
     commence
    0.44
     traslado
    0.44
    Treasurer
    0.43
    誢
    0.43
    Act Density 0.015%

    No Known Activations