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

    Neuronpedia

    INDEX
    Explanations

    agent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tu
    -0.28
     development
    -0.27
     départ
    -0.27
    ëıħ
    -0.26
    åIJĪãĤıãģĽ
    -0.26
    ÑĮÑıн
    -0.26
    æ¹£
    -0.26
    äºĨè¿ĩæĿ¥
    -0.25
    禧
    -0.25
    antine
    -0.25
    POSITIVE LOGITS
    æĮ¹
    0.27
    _unicode
    0.27
    pcs
    0.25
     Kern
    0.25
    robe
    0.25
    OE
    0.25
    >E
    0.24
     reflux
    0.24
    exus
    0.24
    ãģ²
    0.24
    Act Density 1.688%

    No Known Activations