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
    (Resources
    -0.07
    Facing
    -0.06
    _colors
    -0.06
    _enter
    -0.06
     Grid
    -0.06
     Attributes
    -0.06
    fleet
    -0.06
    що
    -0.06
     tờ
    -0.06
    Games
    -0.06
    POSITIVE LOGITS
    .definition
    0.07
     bitcoin
    0.06
     мам
    0.06
    .exc
    0.06
    rometer
    0.06
    сих
    0.06
    &);↵↵
    0.06
    нин
    0.06
    piel
    0.06
    :image
    0.06
    Act Density 0.050%

    No Known Activations