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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hwy
    -0.07
    超
    -0.06
     등
    -0.06
    ':{'
    -0.06
     دین
    -0.06
     Merry
    -0.06
    iqu
    -0.06
     intent
    -0.06
    唯
    -0.06
    159
    -0.06
    POSITIVE LOGITS
     cata
    0.07
     �
    0.07
     Garrett
    0.07
    oplayer
    0.06
    Done
    0.06
     philanth
    0.06
    QRSTUV
    0.06
    ackets
    0.06
    methods
    0.06
     Croatia
    0.06
    Act Density 0.000%

    No Known Activations