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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    20
    -0.07
    oram
    -0.07
     cavern
    -0.07
    man
    -0.07
    am
    -0.07
    xlabel
    -0.07
    emann
    -0.07
    616
    -0.06
     mostra
    -0.06
     leben
    -0.06
    POSITIVE LOGITS
    ()
    0.09
    Third
    0.09
     Third
    0.09
    urd
    0.08
    third
    0.08
     third
    0.08
    Todd
    0.08
    ird
    0.08
    ’d
    0.08
    rd
    0.08
    Act Density 0.110%

    No Known Activations