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

    Neuronpedia

    INDEX
    Explanations

    massive events and phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chap
    0.45
     usual
    0.45
     otherwise
    0.40
     fellow
    0.39
     Grid
    0.39
     Nord
    0.38
     chop
    0.37
    ල්
    0.36
     annoy
    0.36
     alternatively
    0.36
    POSITIVE LOGITS
    ্া
    0.69
    ﷽
    0.68
    📐
    0.67
     বছ
    0.66
     BlueprintName
    0.63
    🥹
    0.62
    🐲
    0.62
     Taehyung
    0.61
     drawSprites
    0.61
    togel
    0.61
    Act Density 0.001%

    No Known Activations