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

    Neuronpedia

    INDEX
    Explanations

    python -m commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waahanga
    0.57
    НЫ
    0.52
    दृ
    0.48
    VERTISING
    0.48
     đích
    0.47
    ըն
    0.47
    CHEN
    0.46
     فراهم
    0.46
     একেবারে
    0.45
    IY
    0.45
    POSITIVE LOGITS
     poesia
    0.63
     essayer
    0.60
     ozone
    0.59
     rob
    0.57
     logiciel
    0.57
     distiller
    0.54
     Evernote
    0.54
     graphene
    0.54
     cleanser
    0.53
     atherosclerosis
    0.53
    Act Density 0.001%

    No Known Activations