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

    Neuronpedia

    INDEX
    Explanations

    program

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yat
    -0.07
     syst
    -0.07
     outline
    -0.07
    (EXPR
    -0.07
    Sr
    -0.07
    .math
    -0.07
    佘
    -0.06
     Lyn
    -0.06
    (xx
    -0.06
     kị
    -0.06
    POSITIVE LOGITS
    ponsible
    0.07
    venues
    0.07
     permissions
    0.07
     współprac
    0.07
    struments
    0.07
    enames
    0.07
    ব
    0.07
    借鉴
    0.07
     MERCHANTABILITY
    0.07
    _creation
    0.07
    Act Density 0.001%

    No Known Activations