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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rhythm
    -0.07
     resisting
    -0.06
    ?>/
    -0.06
     Baum
    -0.06
    سوب
    -0.06
    ùng
    -0.06
     cycle
    -0.06
    &C
    -0.06
    }>{
    -0.06
     vast
    -0.06
    POSITIVE LOGITS
     квітня
    0.06
     Preference
    0.06
    ="";↵
    0.06
    .getUsername
    0.06
    _gradients
    0.06
     Iran
    0.06
    影响
    0.06
     Russia
    0.06
    .SERVER
    0.06
     offshore
    0.06
    Act Density 0.022%

    No Known Activations