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

    Neuronpedia

    INDEX
    Explanations

    methods and inclusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    comb
    -0.06
    Precision
    -0.06
    /configuration
    -0.06
    IDES
    -0.06
    送料無料
    -0.06
     sabotage
    -0.06
    .VisualBasic
    -0.06
     lh
    -0.05
    batch
    -0.05
    cial
    -0.05
    POSITIVE LOGITS
    axis
    0.07
     stad
    0.07
    806
    0.07
    ività
    0.07
    (slug
    0.06
    olin
    0.06
    .sendFile
    0.06
    .setItem
    0.06
     أكتوبر
    0.06
     notebook
    0.06
    Act Density 0.205%

    No Known Activations