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

    Neuronpedia

    INDEX
    Explanations

    arms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GURL
    -0.07
     الصف
    -0.07
     localVar
    -0.07
    額
    -0.07
    ��
    -0.07
    ］
    -0.06
    krv
    -0.06
     near
    -0.06
    snow
    -0.06
     гип
    -0.06
    POSITIVE LOGITS
    unj
    0.07
    вед
    0.06
    eşit
    0.06
    /mp
    0.06
     courses
    0.06
    iad
    0.06
    .Documents
    0.06
     FT
    0.06
     obviously
    0.06
     arms
    0.06
    Act Density 0.006%

    No Known Activations