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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _learn
    -0.06
     Psy
    -0.06
    RequestId
    -0.06
     colspan
    -0.06
    PostalCodes
    -0.06
     бра
    -0.06
    encoded
    -0.06
     analytic
    -0.06
     volunteered
    -0.06
     Mädchen
    -0.06
    POSITIVE LOGITS
     slots
    0.07
    flowers
    0.07
    igator
    0.07
     süreci
    0.07
     Jake
    0.06
    只
    0.06
     Culture
    0.06
     Somali
    0.06
     exponent
    0.06
     ağ
    0.06
    Act Density 0.001%

    No Known Activations