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

    Neuronpedia

    INDEX
    Explanations

    anti

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bead
    -0.07
    Brun
    -0.07
     Zem
    -0.06
     webdriver
    -0.06
     leak
    -0.06
    [N
    -0.06
     AX
    -0.06
     books
    -0.06
    슨
    -0.06
     reached
    -0.06
    POSITIVE LOGITS
    Anti
    0.09
     anti
    0.08
     Anti
    0.08
    TA
    0.08
    ansi
    0.07
    り
    0.07
    ini
    0.07
     semi
    0.07
    io
    0.07
    dı
    0.07
    Act Density 0.036%

    No Known Activations