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

    Neuronpedia

    INDEX
    Explanations

    Parentheses and brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unique
    -0.07
     accom
    -0.07
     incluso
    -0.07
     oluşan
    -0.06
    osy
    -0.06
     convin
    -0.06
    ono
    -0.06
     제품
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
     Крім
    -0.06
    POSITIVE LOGITS
    _ssh
    0.06
    _by
    0.06
     Riot
    0.06
     nIndex
    0.06
    oby
    0.06
     pitching
    0.06
    ective
    0.06
    ції
    0.06
     Horror
    0.06
     Мож
    0.06
    Act Density 0.028%

    No Known Activations