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

    Neuronpedia

    INDEX
    Explanations

    search strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मिटेड
    0.93
    ህል
    0.90
     regelmäßig
    0.86
    Це
    0.84
     అలాగే
    0.84
    стоит
    0.83
    Основ
    0.83
    CVE
    0.83
    mcs
    0.83
    шек
    0.79
    POSITIVE LOGITS
     vä
    0.91
     gray
    0.81
     propagand
    0.78
     divergences
    0.78
     ain
    0.76
     παν
    0.76
     fri
    0.75
     verd
    0.74
     chain
    0.74
     senz
    0.74
    Act Density 0.000%

    No Known Activations