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
    ј
    -0.07
    _ca
    -0.07
    -Clause
    -0.07
    theid
    -0.06
    -0.06
     浙江
    -0.06
     banyak
    -0.06
    _lbl
    -0.06
    #ad
    -0.06
    かり
    -0.06
    POSITIVE LOGITS
    .png
    0.06
    otope
    0.06
     millionaire
    0.06
    ढ
    0.06
     Nightmare
    0.06
     PO
    0.06
    _delivery
    0.06
     Saturday
    0.06
     swim
    0.06
    ierce
    0.06
    Act Density 0.011%

    No Known Activations