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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belirli
    -0.06
    DTV
    -0.06
    CardBody
    -0.06
    IBLE
    -0.06
    /
↵
    -0.06
     throne
    -0.06
    .locale
    -0.06
    _DB
    -0.06
    bit
    -0.06
    Items
    -0.06
    POSITIVE LOGITS
    .rel
    0.07
     amused
    0.06
     Wet
    0.06
     TString
    0.06
    精
    0.06
     softened
    0.06
    ‌کرد
    0.06
    (engine
    0.06
     Sanford
    0.06
    washer
    0.06
    Act Density 0.048%

    No Known Activations