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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cards
    -0.07
    IIIK
    -0.07
    _K
    -0.07
    rei
    -0.07
    epad
    -0.06
    olley
    -0.06
     PCs
    -0.06
    terminate
    -0.06
     Paginator
    -0.06
     Adventures
    -0.06
    POSITIVE LOGITS
     không
    0.07
     Không
    0.07
     sanitizer
    0.07
     Conc
    0.06
     tuy
    0.06
     Marina
    0.06
     exce
    0.06
    Prim
    0.06
     т
    0.06
     Cunningham
    0.06
    Act Density 0.027%

    No Known Activations