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

    Neuronpedia

    INDEX
    Explanations

    L

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ווה
    -0.07
     עסקי
    -0.07
    𝄃
    -0.07
     cree
    -0.06
    -notch
    -0.06
    𝙉
    -0.06
    ngen
    -0.06
    ersion
    -0.06
    Equals
    -0.06
    胖
    -0.06
    POSITIVE LOGITS
     topping
    0.08
     MY
    0.07
     additives
    0.07
    getProperty
    0.07
    バリ
    0.07
     William
    0.07
     Plans
    0.07
    的颜色
    0.07
    _AV
    0.07
     nationality
    0.07
    Act Density 0.014%

    No Known Activations