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

    Neuronpedia

    INDEX
    Explanations

    Control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    beta
    -0.07
    參
    -0.07
     як
    -0.06
     территор
    -0.06
    	Address
    -0.06
    koli
    -0.06
     services
    -0.06
    725
    -0.06
    jb
    -0.06
    825
    -0.06
    POSITIVE LOGITS
     constructing
    0.06
     Pavel
    0.06
     Sous
    0.06
    ━━━━━━━━━━━━━━━━
    0.06
    (completion
    0.06
     animateWithDuration
    0.06
    >↵
    0.06
    иф
    0.06
    خط
    0.06
    _Adjust
    0.06
    Act Density 0.042%

    No Known Activations