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

    Neuronpedia

    INDEX
    Explanations

    "///"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pack
    -0.07
     constraint
    -0.06
     packs
    -0.06
     PACK
    -0.06
     warned
    -0.06
    -mount
    -0.06
     Pair
    -0.06
    Terminal
    -0.06
     contr
    -0.06
     Addr
    -0.06
    POSITIVE LOGITS
    _UNIT
    0.07
     неправиль
    0.07
    lış
    0.06
    ��이지
    0.06
     mystical
    0.06
    FTER
    0.06
    -native
    0.06
    /'.
    0.06
     своє
    0.06
     pohled
    0.06
    Act Density 0.001%

    No Known Activations