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
    Author
    -0.07
     Language
    -0.07
     Gover
    -0.06
    Client
    -0.06
     advantage
    -0.06
    �
    -0.06
    Grant
    -0.06
    specific
    -0.06
     ×
    -0.06
    Z
    -0.06
    POSITIVE LOGITS
     otáz
    0.07
    (para
    0.07
    aepernick
    0.07
    (vertices
    0.06
    (Dictionary
    0.06
    .constant
    0.06
    lexible
    0.06
    〉
    0.06
     blogger
    0.06
     ">
    0.06
    Act Density 0.034%

    No Known Activations