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
    .resize
    -0.06
     TI
    -0.06
     rejo
    -0.06
    Air
    -0.06
    _ignore
    -0.06
    .depth
    -0.06
    RESULTS
    -0.06
     conver
    -0.06
     restr
    -0.06
    sequential
    -0.05
    POSITIVE LOGITS
     before
    0.08
    اوری
    0.07
     등장
    0.07
    riends
    0.07
     behalf
    0.07
    甜
    0.07
     směrem
    0.07
    WAYS
    0.06
     cabo
    0.06
     desde
    0.06
    Act Density 0.244%

    No Known Activations