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

    Neuronpedia

    INDEX
    Explanations

    verbs of action and looking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bienvenidas
    0.31
    यॉर्क
    0.31
     सोर्स
    0.30
     уют
    0.30
    andfeel
    0.29
    юнча
    0.29
    iktar
    0.29
     semangat
    0.29
     என்றும்
    0.29
     disfrut
    0.29
    POSITIVE LOGITS
     muttered
    0.29
     sarcasm
    0.28
     scathing
    0.28
     peck
    0.28
     back
    0.28
     That
    0.28
     buried
    0.28
    Periph
    0.28
     stinging
    0.27
     mutter
    0.27
    Act Density 0.012%

    No Known Activations