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

    Neuronpedia

    INDEX
    Explanations

    power dynamics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HP
    -0.07
    errmsg
    -0.07
     peaks
    -0.06
    ết
    -0.06
     أنه
    -0.06
     Chile
    -0.06
    stackpath
    -0.06
     turns
    -0.06
     دقیق
    -0.06
     전에
    -0.06
    POSITIVE LOGITS
    \core
    0.06
    (metrics
    0.06
     neue
    0.06
    romise
    0.06
    Board
    0.06
     Boolean
    0.06
    =<
    0.06
    %A
    0.06
    Р
    0.06
    当
    0.06
    Act Density 0.072%

    No Known Activations