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
    -so
    -0.07
    appy
    -0.07
     рай
    -0.06
    reff
    -0.06
    ップ
    -0.06
     đảng
    -0.06
     balls
    -0.06
    λου
    -0.06
    sto
    -0.06
     部
    -0.06
    POSITIVE LOGITS
    .blank
    0.07
    ecess
    0.07
    zim
    0.07
     revolves
    0.07
    _typ
    0.06
     Bölüm
    0.06
     recl
    0.06
    =%
    0.06
    vertime
    0.06
    levation
    0.06
    Act Density 0.001%

    No Known Activations