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

    Neuronpedia

    INDEX
    Explanations

    Code/Identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /rec
    -0.26
    ivant
    -0.25
    ioned
    -0.25
    å¥ı
    -0.25
    é¦
    -0.25
    untary
    -0.24
    梯
    -0.24
     QDialog
    -0.24
    ño
    -0.24
    uhn
    -0.24
    POSITIVE LOGITS
    emy
    0.26
    completion
    0.25
    ender
    0.24
     heading
    0.23
    .jupiter
    0.23
     **
    0.23
    identify
    0.22
    è¾ĥ
    0.22
    golden
    0.22
    æĤ²åĵĢ
    0.22
    Act Density 0.000%

    No Known Activations