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

    Neuronpedia

    INDEX
    Explanations

    status post, Kakashi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Storing
    0.53
     ভাইয়ের
    0.50
    ইং
    0.45
     shadowing
    0.42
    Dragging
    0.42
    Sent
    0.41
     Molina
    0.40
    質の
    0.40
    Shadow
    0.39
     Shadow
    0.38
    POSITIVE LOGITS
    ayak
    0.40
     PQ
    0.39
     escaped
    0.39
    escape
    0.39
     karış
    0.38
    plat
    0.38
     loos
    0.38
    fp
    0.37
    ₨
    0.37
     optimised
    0.37
    Act Density 0.004%

    No Known Activations