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

    Neuronpedia

    INDEX
    Explanations

    code and lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Land
    -0.07
     quaternion
    -0.06
    histor
    -0.06
    _find
    -0.06
    Land
    -0.06
     قطع
    -0.06
    Origin
    -0.06
    สาร
    -0.06
    alk
    -0.06
    表
    -0.06
    POSITIVE LOGITS
     nuestros
    0.07
    wing
    0.07
    역시
    0.07
     السعود
    0.06
    ॉप
    0.06
    试
    0.06
    掉
    0.06
    шем
    0.06
    macen
    0.06
     commence
    0.06
    Act Density 0.060%

    No Known Activations