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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     desi
    -0.07
     fatigue
    -0.07
     restrictive
    -0.07
    .TextBox
    -0.07
     didn
    -0.06
    Custom
    -0.06
    
    -0.06
     hardened
    -0.06
    sgiving
    -0.06
     tiêu
    -0.06
    POSITIVE LOGITS
     حسن
    0.07
    aterangepicker
    0.07
    xBE
    0.06
     Celsius
    0.06
    _THAN
    0.06
     قرارداد
    0.06
    xDD
    0.06
    Polygon
    0.06
     элек
    0.06
    xon
    0.06
    Act Density 0.024%

    No Known Activations