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

    Neuronpedia

    INDEX
    Explanations

    ORDER

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -or
    -0.08
    瓢
    -0.07
    roups
    -0.07
     غال
    -0.07
    ひと
    -0.07
    âu
    -0.07
    urons
    -0.06
    /generated
    -0.06
    窭
    -0.06
    -tag
    -0.06
    POSITIVE LOGITS
    SharedPtr
    0.08
    (filter
    0.07
    新建
    0.07
    法规
    0.07
    aida
    0.07
    reira
    0.07
     Touch
    0.07
     compact
    0.07
     Sync
    0.07
    Pink
    0.06
    Act Density 0.000%

    No Known Activations