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

    Neuronpedia

    INDEX
    Explanations

    action verbs followed by and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sesuatu
    0.62
     şeyler
    0.60
    这些人
    0.59
     cosas
    0.58
     something
    0.57
     qualcosa
    0.57
     شيء
    0.54
     ceva
    0.54
     이걸
    0.53
     coś
    0.52
    POSITIVE LOGITS
     and
    0.70
     or
    0.63
     এবং
    0.63
     અને
    0.55
    并
    0.54
     आणि
    0.52
     và
    0.51
     και
    0.51
     மற்றும்
    0.51
    _
    0.50
    Act Density 0.013%

    No Known Activations