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
    popup
    -0.06
    vergence
    -0.06
    Story
    -0.06
    _token
    -0.06
    stance
    -0.06
     ile
    -0.06
    xee
    -0.06
     begin
    -0.06
     Lowell
    -0.06
    .vehicle
    -0.06
    POSITIVE LOGITS
    -<?
    0.07
    ("%.
    0.06
     outfield
    0.06
    538
    0.06
     foul
    0.06
     meilleur
    0.06
     아버지
    0.06
    ']>
    0.06
     влади
    0.06
     JO
    0.06
    Act Density 0.054%

    No Known Activations