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

    Neuronpedia

    INDEX
    Explanations

    aspect ratio, temperature, function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ledger
    0.46
     dissenting
    0.44
     നേര
    0.43
     binder
    0.42
     drawback
    0.42
    ედერ
    0.42
    гле
    0.42
     cringe
    0.42
     harsh
    0.41
     torment
    0.41
    POSITIVE LOGITS
     énorm
    0.55
    lu
    0.50
    她的
    0.49
    yai
    0.49
    ix
    0.49
    getX
    0.49
    q
    0.49
    viv
    0.49
    baz
    0.48
    啊
    0.48
    Act Density 0.001%

    No Known Activations