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

    Neuronpedia

    INDEX
    Explanations

    celebrity gossip articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    provide
    -0.06
     Česká
    -0.06
     smiling
    -0.06
     Woche
    -0.06
     vý
    -0.06
     Isl
    -0.06
     Hispanics
    -0.06
     меся
    -0.06
     люд
    -0.06
     Literature
    -0.06
    POSITIVE LOGITS
    ;i
    0.07
     scraps
    0.06
    Experiment
    0.06
    32
    0.06
    ''.
    0.06
    ESS
    0.06
     arrest
    0.06
     ن
    0.06
    (connectionString
    0.06
    样
    0.06
    Act Density 0.079%

    No Known Activations