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

    Neuronpedia

    INDEX
    Explanations

    box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piv
    -0.07
     geopol
    -0.06
     Huang
    -0.06
    uminium
    -0.06
     minions
    -0.06
     steering
    -0.06
     tsl
    -0.06
     chicago
    -0.06
    )))))↵
    -0.06
     teardown
    -0.05
    POSITIVE LOGITS
    اگر
    0.07
     çok
    0.07
    ازی
    0.07
     Ultra
    0.07
    ellt
    0.07
     cường
    0.07
     narc
    0.06
     بات
    0.06
     Create
    0.06
    ्न
    0.06
    Act Density 0.000%

    No Known Activations