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

    Neuronpedia

    INDEX
    Explanations

    and . ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     franç
    -0.07
    WOOD
    -0.07
    -prop
    -0.07
     Halloween
    -0.06
     prune
    -0.06
    hot
    -0.06
    樹
    -0.06
     dent
    -0.06
     kat
    -0.06
     بال
    -0.06
    POSITIVE LOGITS
     chemotherapy
    0.07
    	true
    0.07
     Роб
    0.06
    обще
    0.06
     골
    0.06
    ोफ
    0.06
     탈
    0.06
     '"';↵
    0.06
     Cyril
    0.06
    iliary
    0.06
    Act Density 0.069%

    No Known Activations