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

    Neuronpedia

    INDEX
    Explanations

    numbers and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حتی
    0.44
     тест
    0.44
     heft
    0.43
     tí
    0.43
     ves
    0.42
     differ
    0.41
     spada
    0.40
     diente
    0.40
     entice
    0.40
     ripping
    0.40
    POSITIVE LOGITS
    φ
    0.42
    zhen
    0.41
    ዞ
    0.41
    Jadi
    0.41
    >{</
    0.40
    helium
    0.39
    solvent
    0.39
    ח
    0.39
    sur
    0.39
    elegant
    0.39
    Act Density 0.006%

    No Known Activations