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

    Neuronpedia

    INDEX
    Explanations

    >>>

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /AFP
    -0.08
    켙
    -0.07
     Tourism
    -0.06
     Stat
    -0.06
    の中
    -0.06
     getField
    -0.06
     consulate
    -0.06
     Coral
    -0.06
    媓
    -0.06
     갖고
    -0.06
    POSITIVE LOGITS
     paid
    0.07
    木
    0.07
    _split
    0.07
    襄阳
    0.07
    ("-",
    0.06
    DisplayName
    0.06
     dla
    0.06
    VALID
    0.06
    avier
    0.06
    Solver
    0.06
    Act Density 0.076%

    No Known Activations