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

    Neuronpedia

    INDEX
    Explanations

    javascript imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.73
    ير
    0.70
    ъ
    0.68
    1
    0.66
    2
    0.62
    one
    0.61
    е
    0.61
    4
    0.59
     one
    0.59
    ва
    0.59
    POSITIVE LOGITS
     HashSet
    0.52
     incarceration
    0.51
     adhesions
    0.49
     போது
    0.48
    iapan
    0.48
    啍
    0.48
    біт
    0.48
     separations
    0.47
     installers
    0.47
     TODO
    0.47
    Act Density 0.000%

    No Known Activations