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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    واز
    -0.06
     intervention
    -0.06
     تازه
    -0.06
    athlon
    -0.06
    翼
    -0.06
    .JComboBox
    -0.06
    .rstrip
    -0.06
     채용
    -0.06
     Pepper
    -0.06
    埃
    -0.06
    POSITIVE LOGITS
    िह
    0.07
    ),(
    0.06
    ]</
    0.06
     arte
    0.06
    Earn
    0.06
     hydro
    0.06
    των
    0.06
    _take
    0.06
     mem
    0.06
     und
    0.06
    Act Density 0.021%

    No Known Activations