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

    Neuronpedia

    INDEX
    Explanations

    fish and seafood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raphene
    0.43
     Pion
    0.42
     lineare
    0.39
    LinearLayout
    0.38
     cree
    0.38
    芨
    0.38
     toric
    0.37
    蜱
    0.37
     delegated
    0.37
     responsive
    0.37
    POSITIVE LOGITS
     sardines
    1.48
     sard
    1.32
     anch
    1.30
     Sard
    1.21
     herring
    1.13
     Anch
    1.10
     mackerel
    0.97
    Anch
    0.95
    鰯
    0.90
     squid
    0.83
    Act Density 0.014%

    No Known Activations