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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     organization
    -0.07
     sscanf
    -0.07
    sen
    -0.06
     김
    -0.06
     deviations
    -0.06
    AILS
    -0.06
     тка
    -0.06
     trab
    -0.06
     consort
    -0.06
    ContextHolder
    -0.06
    POSITIVE LOGITS
    ñana
    0.07
     Alt
    0.07
     Plat
    0.06
    .virtual
    0.06
     Carrier
    0.06
    bigint
    0.06
     mechanic
    0.06
     lac
    0.06
    imary
    0.06
    0.06
    Act Density 0.018%

    No Known Activations