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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alarm
    -0.07
    rese
    -0.07
     slur
    -0.06
    füg
    -0.06
     Singles
    -0.06
    Merge
    -0.06
     speeds
    -0.06
    졌다
    -0.06
    यर
    -0.06
    dm
    -0.06
    POSITIVE LOGITS
    ête
    0.08
    slick
    0.07
    otherapy
    0.06
    ,y
    0.06
    #aa
    0.06
    /ca
    0.06
     Foo
    0.06
     Не
    0.06
    pter
    0.06
    اورزی
    0.06
    Act Density 0.037%

    No Known Activations