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
     advertised
    -0.06
    ,tmp
    -0.06
    ,test
    -0.06
     weir
    -0.06
    .deck
    -0.06
    !!!!!
    -0.06
    	tmp
    -0.06
     spice
    -0.06
     mongoose
    -0.06
     borderline
    -0.06
    POSITIVE LOGITS
    As
    0.07
    _FIRST
    0.07
    At
    0.07
     On
    0.07
    _on
    0.06
    polygon
    0.06
    -eyed
    0.06
    لت
    0.06
     Dies
    0.06
    _GRE
    0.06
    Act Density 0.027%

    No Known Activations