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

    Neuronpedia

    INDEX
    Explanations

    No

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mux
    -0.07
     díl
    -0.07
    filer
    -0.07
    —a
    -0.07
     navbar
    -0.06
     goalt
    -0.06
     ■
    -0.06
     rod
    -0.06
     story
    -0.06
     divider
    -0.06
    POSITIVE LOGITS
     구글상위
    0.07
    LEN
    0.06
     bak
    0.06
    .GetUser
    0.06
    nave
    0.06
     accelerate
    0.06
    =root
    0.06
    tright
    0.06
    	http
    0.06
    Ur
    0.06
    Act Density 0.001%

    No Known Activations