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

    Neuronpedia

    INDEX
    Explanations

    ):

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     groceries
    -0.06
    .QLabel
    -0.06
    ER
    -0.06
    Convert
    -0.06
     民
    -0.06
    .setup
    -0.06
    .delta
    -0.06
    Freq
    -0.06
    搭
    -0.06
    .LOC
    -0.06
    POSITIVE LOGITS
     δε
    0.06
     kaç
    0.06
    있
    0.06
    ewitness
    0.06
    项
    0.06
     quand
    0.06
    voor
    0.06
    Due
    0.06
    ную
    0.06
     fileSize
    0.06
    Act Density 0.002%

    No Known Activations