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

    Neuronpedia

    INDEX
    Explanations

    location prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    textfield
    -0.09
    )[
    -0.07
    难
    -0.07
    VERSION
    -0.06
    -bound
    -0.06
     г
    -0.06
     matchup
    -0.06
    مه
    -0.06
    า�
    -0.06
    category
    -0.06
    POSITIVE LOGITS
    mıyor
    0.06
     ordinances
    0.06
    mir
    0.06
     خانم
    0.06
    ému
    0.06
     �
    0.06
     uphe
    0.06
     istiyorum
    0.06
    (","
    0.06
    啊
    0.06
    Act Density 0.043%

    No Known Activations