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

    Neuronpedia

    INDEX
    Explanations

    Tone Clock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crem
    0.39
    してみました
    0.39
    __))
    0.37
    بعا
    0.36
     assemblies
    0.36
    。【
    0.36
    しました
    0.35
     recoverable
    0.35
     Ав
    0.35
    送到
    0.35
    POSITIVE LOGITS
    繃
    0.38
    دا
    0.38
     unset
    0.36
    үүн
    0.36
    ungle
    0.36
    inib
    0.36
    ರ
    0.35
     explic
    0.35
     oublier
    0.35
     tepi
    0.35
    Act Density 0.000%

    No Known Activations