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

    Neuronpedia

    INDEX
    Explanations

    Code and technical jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usable
    -0.27
    åĩŃ
    -0.24
    ]){
    -0.24
    ä¸Ģç§į
    -0.23
    ________
    -0.23
    hang
    -0.23
     neighbourhood
    -0.23
    Pawn
    -0.23
    cancel
    -0.23
    ä¹ĥ
    -0.23
    POSITIVE LOGITS
    éĺª
    0.28
     refl
    0.28
    æĶ¹æŃ£
    0.27
    建
    0.27
    裹
    0.25
    ä½³
    0.25
    ↵                ↵
    0.24
     Rated
    0.24
     critique
    0.24
     gas
    0.23
    Act Density 0.656%

    No Known Activations