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

    Neuronpedia

    INDEX
    Explanations

    dolphins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    耱
    0.19
    0.18
     менедже
    0.18
     clockRadius
    0.18
    >∕</
    0.18
     nCmd
    0.18
     elytris
    0.17
    ⟋
    0.17
    0.17
    tidy
    0.17
    POSITIVE LOGITS
     dolphin
    0.19
     dolphins
    0.18
     Dolphins
    0.18
    dent
    0.18
     poster
    0.17
    。...
    0.17
     Dolphin
    0.17
    da
    0.17
     teeth
    0.17
    uous
    0.17
    Act Density 0.233%

    No Known Activations