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

    Neuronpedia

    INDEX
    Explanations

    command words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ತ್ರಿ
    0.27
     gloves
    0.26
     extremadamente
    0.26
    εια
    0.26
     estremamente
    0.26
     pues
    0.25
     sorely
    0.25
     cosi
    0.24
    헙
    0.24
     மிகவும்
    0.24
    POSITIVE LOGITS
    ل
    0.30
    y
    0.29
    opium
    0.28
    org
    0.26
    w
    0.26
    t
    0.25
    warn
    0.25
    ors
    0.25
    мут
    0.24
    ul
    0.24
    Act Density 1.181%

    No Known Activations