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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs/prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Detailed
    -0.08
    兵
    -0.06
    анням
    -0.06
    IRON
    -0.06
    mach
    -0.06
    WXYZ
    -0.06
    _proj
    -0.06
     miscellaneous
    -0.06
     enclosed
    -0.06
     detailed
    -0.06
    POSITIVE LOGITS
    .netty
    0.07
     файл
    0.06
    GBT
    0.06
    €“
    0.06
    گیری
    0.06
     ~
    0.06
     não
    0.06
    (xml
    0.06
    -------↵↵
    0.06
     cpt
    0.06
    Act Density 0.251%

    No Known Activations