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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    START
    -0.08
    是一项
    -0.07
    きっかけ
    -0.07
    ầm
    -0.07
    DER
    -0.07
     turned
    -0.07
    𐤓
    -0.07
    bezpieczeńst
    -0.07
    search
    -0.07
    .setToolTipText
    -0.06
    POSITIVE LOGITS
     elast
    0.07
     Reco
    0.07
    ⿊
    0.07
     quietly
    0.07
     estable
    0.06
    slick
    0.06
     пен
    0.06
     arbitr
    0.06
    ])))↵
    0.06
    }));↵↵
    0.06
    Act Density 0.004%

    No Known Activations