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

    Neuronpedia

    INDEX
    Explanations

    Internet user interactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棣
    -0.07
    ersive
    -0.07
    .masksToBounds
    -0.07
     benefits
    -0.07
    .forChild
    -0.06
     adec
    -0.06
     Clover
    -0.06
     newName
    -0.06
     ly
    -0.06
    _cfg
    -0.06
    POSITIVE LOGITS
    bud
    0.07
    throws
    0.07
    pora
    0.06
    different
    0.06
    מתח
    0.06
    :NSMakeRange
    0.06
     terrorist
    0.06
     Anat
    0.06
    startDate
    0.06
    (grammar
    0.06
    Act Density 0.050%

    No Known Activations