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

    Neuronpedia

    INDEX
    Explanations

    Maintain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Encore
    -0.07
    making
    -0.07
     अगल
    -0.06
    Keyword
    -0.06
    тов
    -0.06
     Msg
    -0.06
    باشد
    -0.06
    [%
    -0.06
    .public
    -0.06
    aff
    -0.06
    POSITIVE LOGITS
     παν
    0.06
    _RECT
    0.06
    逐
    0.06
    inan
    0.06
     meticulous
    0.06
     Ngb
    0.06
     loved
    0.06
    (properties
    0.06
     panic
    0.06
     }()↵
    0.06
    Act Density 0.052%

    No Known Activations