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
    rett
    -0.08
    urt
    -0.07
    頓
    -0.07
    zer
    -0.07
    pleado
    -0.07
    垛
    -0.07
     TIMER
    -0.06
    เต
    -0.06
    leo
    -0.06
    umpt
    -0.06
    POSITIVE LOGITS
     mixins
    0.08
     aVar
    0.07
    ᨕ
    0.07
     __("
    0.07
    (\'
    0.07
     handic
    0.07
    >({↵
    0.07
     cravings
    0.06
    备考
    0.06
     "*"
    0.06
    Act Density 0.002%

    No Known Activations