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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sec
    -0.07
    نين
    -0.06
    (errors
    -0.06
     gusto
    -0.06
     suicides
    -0.06
    OKEN
    -0.06
    (turn
    -0.06
    ften
    -0.06
    ecs
    -0.06
    _Find
    -0.06
    POSITIVE LOGITS
     blockDim
    0.07
     πολι
    0.06
    _SOCKET
    0.06
     Suddenly
    0.06
    esser
    0.06
    leyici
    0.06
    _la
    0.06
    :,
    0.06
     Velvet
    0.06
    institution
    0.06
    Act Density 0.020%

    No Known Activations