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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _wind
    -0.07
    ocker
    -0.06
     dismissal
    -0.06
    řiv
    -0.06
    ูนย
    -0.06
    pseudo
    -0.06
     logistic
    -0.06
     respecto
    -0.06
    lep
    -0.06
    Regression
    -0.06
    POSITIVE LOGITS
    oref
    0.07
     Борис
    0.07
     Once
    0.06
     emergencies
    0.06
    	page
    0.06
    تغ
    0.06
     Click
    0.06
     DatabaseReference
    0.06
    .ReadInt
    0.06
    十二
    0.06
    Act Density 0.025%

    No Known Activations