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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ct
    -0.06
     đu
    -0.06
    ARG
    -0.06
    addons
    -0.06
     laundering
    -0.06
    Will
    -0.06
     مب
    -0.06
    deep
    -0.06
     würde
    -0.06
     sẵn
    -0.06
    POSITIVE LOGITS
    temperature
    0.07
     Lions
    0.06
     hypothesis
    0.06
     Computational
    0.06
    '},↵
    0.06
     nhập
    0.06
     configurations
    0.06
    .Some
    0.06
    =''↵
    0.06
    TRS
    0.06
    Act Density 0.021%

    No Known Activations