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

    Neuronpedia

    INDEX
    Explanations

    Dates and updates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仮
    -0.07
    _para
    -0.06
     nových
    -0.06
    uck
    -0.06
    好的
    -0.06
    ustainability
    -0.06
    前的
    -0.06
    =date
    -0.06
    Poss
    -0.06
    (place
    -0.06
    POSITIVE LOGITS
    updating
    0.07
    حص
    0.07
    _PIXEL
    0.07
    rightarrow
    0.07
    оне
    0.07
    ihil
    0.06
     baseURL
    0.06
    ула
    0.06
     assumptions
    0.06
    (Role
    0.06
    Act Density 0.001%

    No Known Activations