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

    Neuronpedia

    INDEX
    Explanations

    aggressive or assertive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इंपॉर्टेंट
    0.53
    Create
    0.51
    و
    0.51
    ச்சூழ
    0.50
    RAM
    0.49
     Всё
    0.49
     rotates
    0.48
     estrellas
    0.48
    plexity
    0.48
    BySize
    0.47
    POSITIVE LOGITS
     aggressively
    0.71
     aggressive
    0.66
    पणे
    0.66
     agress
    0.63
     harsher
    0.60
     harshly
    0.59
     assertive
    0.58
     unapolog
    0.58
     outspoken
    0.57
    aggressive
    0.57
    Act Density 0.086%

    No Known Activations