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

    Neuronpedia

    INDEX
    Explanations

    reserved rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ща
    -0.75
     menuItem
    -0.71
    決め
    -0.70
    throws
    -0.69
    tido
    -0.68
    seling
    -0.68
    到现在
    -0.66
     (;;
    -0.66
    rode
    -0.66
    主役
    -0.64
    POSITIVE LOGITS
    VOD
    0.71
     😢
    0.71
     capri
    0.70
    spare
    0.70
    Ingreso
    0.68
     camo
    0.68
     🙏
    0.68
     Dox
    0.67
    isEmail
    0.67
     colombia
    0.67
    Act Density 0.050%

    No Known Activations