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

    Neuronpedia

    INDEX
    Explanations

    actions of doing, feeling, or thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overfitting
    0.46
    putting
    0.45
     нарушения
    0.44
     willingness
    0.44
     окончания
    0.43
     ঠিকানা
    0.43
     ধারাবাহিক
    0.42
     sharpness
    0.42
     waterfalls
    0.41
     freshness
    0.41
    POSITIVE LOGITS
     categorize
    0.57
     emote
    0.57
     legislate
    0.56
     innovate
    0.56
    Analyze
    0.54
     theor
    0.53
     analyze
    0.50
     Pray
    0.50
     prayed
    0.49
     Analyze
    0.49
    Act Density 0.036%

    No Known Activations