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

    Neuronpedia

    INDEX
    Explanations

    Greek letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     há
    -0.08
    sj
    -0.08
    Ve
    -0.08
     miniature
    -0.07
    EMP
    -0.07
     hängen
    -0.07
    لەر
    -0.07
     Ve
    -0.07
     Fed
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    wet
    0.08
    没
    0.08
     burnt
    0.07
    _include
    0.07
     وس
    0.07
     Willow
    0.07
    _wh
    0.07
     Wh
    0.07
     Keith
    0.07
     agit
    0.07
    Act Density 0.026%

    No Known Activations