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

    Neuronpedia

    INDEX
    Explanations

    code and date formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sparse
    -0.07
     Speak
    -0.07
     Modal
    -0.07
    듯
    -0.07
     chips
    -0.06
     Git
    -0.06
    ائل
    -0.06
    Share
    -0.06
     dialect
    -0.06
    elize
    -0.06
    POSITIVE LOGITS
     migrant
    0.06
    оги
    0.06
    .LAZY
    0.06
    拳
    0.06
     Fragen
    0.06
    KD
    0.06
     miglior
    0.06
    reation
    0.06
     CSL
    0.06
    ＼＼
    0.06
    Act Density 0.147%

    No Known Activations