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

    Neuronpedia

    INDEX
    Explanations

    academic citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่อต
    -0.07
    ับสน
    -0.07
     ملت
    -0.06
    ностей
    -0.06
    nů
    -0.06
     руковод
    -0.06
     sổ
    -0.06
     přísluš
    -0.06
     appliance
    -0.06
    entimes
    -0.06
    POSITIVE LOGITS
     Fans
    0.07
     improvis
    0.06
     shook
    0.06
     *>(
    0.06
     matches
    0.06
     Unlock
    0.06
     recognizer
    0.06
     Awareness
    0.06
     Wrap
    0.06
     ElseIf
    0.06
    Act Density 0.009%

    No Known Activations