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

    Neuronpedia

    INDEX
    Explanations

    cales

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stuff
    -0.07
     jednak
    -0.06
    bie
    -0.06
    urrenc
    -0.06
    Portland
    -0.06
    Public
    -0.06
    MC
    -0.06
     predicate
    -0.06
     Anyway
    -0.06
    (Value
    -0.06
    POSITIVE LOGITS
    eni
    0.06
    ไว
    0.06
     summed
    0.06
    іїв
    0.06
     この
    0.06
     Infer
    0.06
    lâm
    0.06
    _listing
    0.06
     Lemon
    0.06
    其实
    0.06
    Act Density 0.102%

    No Known Activations