Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Taco Tuesday

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ர்ப
    0.45
     pok
    0.42
     dim
    0.42
    ponds
    0.41
     cubo
    0.40
     pond
    0.39
    cub
    0.39
     pó
    0.38
     peaches
    0.38
    pond
    0.37
    POSITIVE LOGITS
    🌮
    0.79
     shells
    0.76
     taco
    0.75
     Tuesday
    0.68
    shells
    0.68
     Taco
    0.65
    Tuesday
    0.63
     shell
    0.63
     Shell
    0.59
    殼
    0.59
    Act Density 0.006%

    No Known Activations