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

    Neuronpedia

    INDEX
    Explanations

    variable or keyword followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ඃ
    0.87
    OMX
    0.87
    tmux
    0.86
     नती
    0.86
    LensFlare
    0.84
     léz
    0.83
     compiles
    0.83
    ㄺ
    0.83
     adware
    0.83
     fable
    0.83
    POSITIVE LOGITS
     blood
    0.61
     ang
    0.57
     near
    0.53
    比
    0.52
     your
    0.51
     kanyang
    0.51
     self
    0.50
    抖
    0.49
    ens
    0.49
    您
    0.49
    Act Density 0.384%

    No Known Activations