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

    Neuronpedia

    INDEX
    Explanations

    Code events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ఖ
    -0.08
     deviations
    -0.08
     పొ
    -0.08
     repro
    -0.08
    .Concurrent
    -0.07
     pyramid
    -0.07
    ateness
    -0.07
     kostenlos
    -0.07
     inequalities
    -0.07
     pains
    -0.07
    POSITIVE LOGITS
    onclick
    0.09
     onclick
    0.09
    .onclick
    0.09
     handler
    0.08
    handler
    0.08
    gw
    0.08
     btn
    0.08
     href
    0.08
    	handler
    0.08
    lec
    0.08
    Act Density 0.006%

    No Known Activations