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

    Neuronpedia

    INDEX
    Explanations

    poem, PHP, generate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     магистра
    0.47
    Acceler
    0.46
     கொ
    0.43
    galo
    0.43
    dan
    0.43
     जिनसे
    0.43
     tatsächlich
    0.42
    MEAN
    0.42
    leftrightarrow
    0.42
     कहान
    0.42
    POSITIVE LOGITS
     jeweil
    0.51
     Spinach
    0.50
     vegetables
    0.49
    وجه
    0.47
     Seite
    0.45
     selector
    0.45
     plants
    0.45
     tanaman
    0.44
     comparison
    0.44
    asan
    0.44
    Act Density 0.001%

    No Known Activations