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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¸į解
    -0.31
    edo
    -0.29
    -pane
    -0.28
    etu
    -0.28
    izio
    -0.27
    itte
    -0.26
    æĿłæĿĨ
    -0.26
    åį¤
    -0.26
    eson
    -0.25
     Kens
    -0.25
    POSITIVE LOGITS
    WF
    0.28
    ORIZATION
    0.27
     temptation
    0.27
    ophilia
    0.25
    ¬
    0.25
    vidence
    0.24
    Restore
    0.24
    åĩŃ
    0.24
    ÑģÑĭл
    0.23
    /ajax
    0.23
    Act Density 0.362%

    No Known Activations