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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umor
    -0.07
    (handle
    -0.07
    čů
    -0.07
     My
    -0.07
     adjacency
    -0.06
     immunity
    -0.06
    =int
    -0.06
     условия
    -0.06
    res
    -0.06
    íg
    -0.06
    POSITIVE LOGITS
    728
    0.06
    하려
    0.06
    ////////////////////////////////////////////////////////
    0.06
    836
    0.06
     побед
    0.06
    encrypted
    0.06
     Heal
    0.06
    orum
    0.06
    平
    0.06
    ै.
    0.06
    Act Density 0.000%

    No Known Activations