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

    Neuronpedia

    INDEX
    Explanations

    sensitivities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    èĩªæŁ¥
    -0.28
    -ne
    -0.27
    åIJĦè¡Į
    -0.26
     taped
    -0.25
    ä½łæĥ³
    -0.25
    åĢŁåı£
    -0.25
    western
    -0.25
    -band
    -0.25
    precation
    -0.25
     lazy
    -0.24
    POSITIVE LOGITS
    æ¿¡
    0.31
    afc
    0.27
     irrit
    0.26
    rz
    0.26
    ppe
    0.26
    人群ä¸Ń
    0.26
     smells
    0.25
     overlaps
    0.25
    .navigate
    0.25
     climates
    0.25
    Act Density 0.002%

    No Known Activations