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

    Neuronpedia

    INDEX
    Explanations

    Figures and supplementary materials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DisplayName
    -0.06
     منه
    -0.06
     humano
    -0.06
    ;;;;;;;;
    -0.06
    >.↵↵
    -0.06
    луб
    -0.06
    同じ
    -0.06
    ление
    -0.06
    quisition
    -0.06
    chte
    -0.06
    POSITIVE LOGITS
     pastry
    0.07
     neighbouring
    0.06
    ी-
    0.06
    ngx
    0.06
    َج
    0.06
    XX
    0.06
     GLfloat
    0.06
    _RGCTX
    0.06
    _CHARS
    0.06
     eligibility
    0.06
    Act Density 0.001%

    No Known Activations