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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fügung
    -0.08
     μην
    -0.08
     instructions
    -0.08
     concaten
    -0.07
     inutil
    -0.07
     grandchildren
    -0.07
     pern
    -0.07
     lösen
    -0.07
     FIXME
    -0.07
     расстоя
    -0.07
    POSITIVE LOGITS
    认证
    0.11
    Awards
    0.11
     prestigious
    0.11
     praised
    0.10
     선정
    0.10
     ಪ್ರಶ
    0.10
     boutique
    0.10
    👏
    0.10
     인증
    0.09
     призн
    0.09
    Act Density 0.198%

    No Known Activations