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

    Neuronpedia

    INDEX
    Explanations

    many searching or figuring out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jogador
    0.51
    Bert
    0.46
    ODE
    0.46
    ，
    0.44
    OL
    0.44
    Pand
    0.44
    Gamb
    0.42
    ،
    0.42
    Tensor
    0.42
    Laser
    0.42
    POSITIVE LOGITS
     实现
    0.45
     因此
    0.45
    ovali
    0.45
    смотря
    0.45
     યોજના
    0.45
     పొ
    0.44
     소녀
    0.44
     பெறும்
    0.43
    häng
    0.42
     přip
    0.42
    Act Density 0.001%

    No Known Activations