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

    Neuronpedia

    INDEX
    Explanations

    code blocks ending with else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Classes
    0.78
    Class
    0.76
     Classes
    0.74
     Extension
    0.74
    িউ
    0.73
    خم
    0.71
     class
    0.71
    Extension
    0.71
     Crav
    0.70
     Class
    0.69
    POSITIVE LOGITS
     ठिका
    0.63
     scored
    0.61
    ้อน
    0.60
     savings
    0.60
    ]];
    0.60
     हानि
    0.59
    ேட்
    0.58
     only
    0.58
    antik
    0.58
    yming
    0.56
    Act Density 0.088%

    No Known Activations