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

    Neuronpedia

    INDEX
    Explanations

    useful

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /NĐ
    -0.07
    Sus
    -0.07
    „D
    -0.07
     JPEG
    -0.07
     cowboy
    -0.06
    _Enc
    -0.06
    장
    -0.06
    líž
    -0.06
    Tour
    -0.06
     ApplicationUser
    -0.06
    POSITIVE LOGITS
    !(↵
    0.06
    Accepted
    0.06
    ADED
    0.06
    egra
    0.06
    azine
    0.06
    izzling
    0.06
    oucí
    0.06
     PodsDummy
    0.06
    _comb
    0.06
    0.06
    Act Density 0.078%

    No Known Activations