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

    Neuronpedia

    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    143
    -0.07
     сторон
    -0.07
    Income
    -0.07
    ób
    -0.07
    цем
    -0.06
    TURN
    -0.06
     pains
    -0.06
     mots
    -0.06
    Segment
    -0.06
    };
↵
    -0.06
    POSITIVE LOGITS
    İT
    0.07
    embourg
    0.06
    .is
    0.06
    _US
    0.06
     Cre
    0.06
    정이
    0.06
    ожет
    0.06
     cra
    0.06
     Ninth
    0.06
    ユ
    0.06
    Act Density 0.079%

    No Known Activations