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

    Neuronpedia

    INDEX
    Explanations

    potato dumplings and spätzle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unnumbered
    0.41
     округу
    0.41
     العل
    0.37
    >∞</
    0.37
    Bend
    0.36
    args
    0.36
    栀
    0.35
     Gord
    0.35
     Filosof
    0.35
     ఫో
    0.35
    POSITIVE LOGITS
     bump
    0.42
    챈
    0.40
     채
    0.39
     calda
    0.38
    bump
    0.38
    െന്നാണ്
    0.37
     decay
    0.37
     pane
    0.37
    persona
    0.37
     égard
    0.37
    Act Density 0.007%

    No Known Activations