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

    Neuronpedia

    INDEX
    Explanations

    Period character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Uri
    -0.07
    олева
    -0.06
    PX
    -0.06
     přesně
    -0.06
    _Y
    -0.06
    upakan
    -0.06
    _EV
    -0.06
    In
    -0.06
     Oliveira
    -0.06
    rupa
    -0.06
    POSITIVE LOGITS
     vů
    0.07
     compan
    0.07
     umění
    0.07
    	button
    0.06
     přest
    0.06
     knack
    0.06
    Brit
    0.06
    	clock
    0.06
    ологичес
    0.06
    .verbose
    0.06
    Act Density 0.006%

    No Known Activations