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

    Neuronpedia

    INDEX
    Explanations

    screen dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ikat
    0.39
     Markus
    0.39
     sphinx
    0.39
     приро
    0.38
     migrating
    0.38
     mew
    0.38
    ]/(
    0.37
     cinta
    0.37
     eti
    0.37
     понять
    0.36
    POSITIVE LOGITS
     Venom
    0.40
    Hourly
    0.40
    proficiency
    0.39
    Priority
    0.38
    iske
    0.38
    disciplinary
    0.38
    agiarism
    0.38
     Proficiency
    0.38
    iser
    0.37
    Last
    0.37
    Act Density 0.000%

    No Known Activations