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

    Neuronpedia

    INDEX
    Explanations

    driven or drawn by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    વાલ
    0.72
    在一起
    0.66
     overcrowded
    0.65
    谢谢
    0.65
    并
    0.65
    arians
    0.64
    。『
    0.64
    iant
    0.64
     складі
    0.64
    Dic
    0.63
    POSITIVE LOGITS
     Motiv
    0.79
     motivated
    0.68
     precipit
    0.67
    裹
    0.67
    devkit
    0.65
     motiv
    0.64
     refused
    0.64
     Linux
    0.64
     கட்டு
    0.63
     이미
    0.62
    Act Density 0.051%

    No Known Activations