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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fich
    -0.07
     wanna
    -0.06
     verifying
    -0.06
     photon
    -0.06
    licas
    -0.06
    に対
    -0.06
     chois
    -0.06
     oraz
    -0.06
     фай
    -0.06
     Πέ
    -0.05
    POSITIVE LOGITS
    {}↵↵
    0.07
    _phrase
    0.07
     différentes
    0.07
     Jen
    0.07
     DbType
    0.07
    uddenly
    0.06
    Thread
    0.06
     thần
    0.06
     anthropology
    0.06
    _modify
    0.06
    Act Density 0.014%

    No Known Activations