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

    Neuronpedia

    INDEX
    Explanations

    tr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrongdoing
    -0.07
    .Locale
    -0.07
    hot
    -0.07
     conductivity
    -0.07
     Debug
    -0.06
     '':↵
    -0.06
    สถาน
    -0.06
     fries
    -0.06
    engo
    -0.06
     olduğundan
    -0.06
    POSITIVE LOGITS
    !”
    0.06
     Valve
    0.06
    ělí
    0.06
    (value
    0.06
     [(
    0.06
    _enter
    0.06
     outr
    0.06
    詳細
    0.06
     Flu
    0.06
     نسبت
    0.06
    Act Density 0.044%

    No Known Activations