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

    Neuronpedia

    INDEX
    Explanations

    data structures, programming, content types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Collision
    0.60
    Collision
    0.59
    Z
    0.54
     collision
    0.47
    сів
    0.47
    ZUKI
    0.46
    旂
    0.45
    િતા
    0.44
    兕
    0.44
    Dz
    0.44
    POSITIVE LOGITS
     baisse
    0.50
    ्या
    0.48
     magnets
    0.47
     dimers
    0.46
    lots
    0.45
     supermarkets
    0.45
    cited
    0.45
     condiments
    0.44
     refrigerators
    0.44
     sprinkles
    0.44
    Act Density 0.000%

    No Known Activations