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

    Neuronpedia

    INDEX
    Explanations

    ongoing fallout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     towns
    0.42
     conducting
    0.42
     launches
    0.42
     obce
    0.42
     unserem
    0.41
     citizens
    0.40
     villages
    0.40
     unsere
    0.40
    bé
    0.40
     unseren
    0.40
    POSITIVE LOGITS
    ynn
    0.52
    dry
    0.46
     Drawable
    0.46
    zigzag
    0.44
    пенди
    0.43
    yn
    0.42
    Complex
    0.42
    Dry
    0.42
    rm
    0.41
    String
    0.41
    Act Density 7.515%

    No Known Activations