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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    truncate
    -0.08
     Peacock
    -0.08
    *j
    -0.07
     iv
    -0.07
     juta
    -0.07
    áp
    -0.07
     Ivory
    -0.07
     तरीका
    -0.07
    Random
    -0.07
     consistente
    -0.07
    POSITIVE LOGITS
     notions
    0.10
    лению
    0.08
     현실
    0.08
     somehow
    0.08
    ੱਗ
    0.08
     scales
    0.08
     ਨਾਲ
    0.08
     развитию
    0.07
     elkaar
    0.07
     produced
    0.07
    Act Density 0.171%

    No Known Activations