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

    Neuronpedia

    INDEX
    Explanations

    slang or jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abdul
    -0.07
    dependent
    -0.06
     bounding
    -0.06
     hanging
    -0.06
     obstruction
    -0.06
     pentru
    -0.06
     directors
    -0.06
    ี้
    -0.06
     dancers
    -0.06
     Suite
    -0.06
    POSITIVE LOGITS
     золот
    0.07
    pretty
    0.06
     cute
    0.06
    Ÿ
    0.06
    benhavn
    0.06
     піз
    0.06
     comboBox
    0.06
    셨
    0.06
    .forEach
    0.06
    .TRA
    0.06
    Act Density 0.086%

    No Known Activations