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
     Message
    -0.07
    Inner
    -0.07
    _ch
    -0.06
     Buildings
    -0.06
     شي
    -0.06
     online
    -0.06
    ather
    -0.06
     belief
    -0.06
    Median
    -0.06
     Games
    -0.06
    POSITIVE LOGITS
     Erot
    0.07
     Giới
    0.07
    _UTF
    0.06
    ्वत
    0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.06
     Sheffield
    0.06
     disen
    0.06
    _download
    0.06
    онь
    0.06
     ऋ
    0.06
    Act Density 0.068%

    No Known Activations