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

    Neuronpedia

    INDEX
    Explanations

    language models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    0.60
    :
    0.50
    ia
    0.49
    /
    0.49
    -
    0.48
    R
    0.48
     neuropathy
    0.47
     vitality
    0.47
    א
    0.47
    ing
    0.46
    POSITIVE LOGITS
     textes
    0.60
     ogrom
    0.59
     व्याकरण
    0.59
     શબ્
    0.59
     Вол
    0.57
     feuilles
    0.56
     ustedes
    0.56
     jūs
    0.56
     நீங்கள்
    0.55
     nagyon
    0.55
    Act Density 1.940%

    No Known Activations