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

    Neuronpedia

    INDEX
    Explanations

    abstraction and representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    σταν
    0.45
     unethical
    0.43
     तकनीकी
    0.42
    aini
    0.42
     technischen
    0.41
     modernization
    0.40
     friendliness
    0.40
    μφωνα
    0.40
    पास
    0.39
     spécifiques
    0.39
    POSITIVE LOGITS
     cognitive
    1.07
     Cognitive
    1.00
    Cogn
    0.98
    cognitive
    0.93
     cognition
    0.91
     cognit
    0.88
     mental
    0.86
     Reasoning
    0.80
     cognitiva
    0.80
     Mental
    0.80
    Act Density 0.042%

    No Known Activations