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
    562
    -0.08
     lug
    -0.07
    Touches
    -0.07
    785
    -0.07
    782
    -0.06
     olup
    -0.06
    _Speed
    -0.06
    baz
    -0.06
    .ForeColor
    -0.06
    	dto
    -0.06
    POSITIVE LOGITS
    ADOW
    0.07
     напрям
    0.06
     GRAT
    0.06
     durations
    0.06
    ivalence
    0.06
    _PHP
    0.06
    Meal
    0.06
    Gu
    0.06
     Metadata
    0.06
    .arch
    0.06
    Act Density 0.076%

    No Known Activations