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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enstein
    -0.27
     Monument
    -0.26
    æĪĺåľºä¸Ĭ
    -0.24
     engineered
    -0.24
    db
    -0.24
    ä½łåĢij
    -0.24
     Engineer
    -0.24
    dlg
    -0.23
    U
    -0.23
    läss
    -0.23
    POSITIVE LOGITS
     Particularly
    0.28
    uche
    0.28
    åĨĮ
    0.28
    é¢ł
    0.27
    ä¸įåĪĨ
    0.27
    (lib
    0.27
    onces
    0.26
    åIJ¬åIJ¬
    0.26
    oga
    0.26
    å°¤
    0.26
    Act Density 0.010%

    No Known Activations