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

    Neuronpedia

    INDEX
    Explanations

    Starts, Paste, or find maximum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colds
    0.39
     diuretics
    0.35
     ecosystems
    0.35
     vasculature
    0.35
     can
    0.34
     whales
    0.33
     lizards
    0.32
     tides
    0.32
     petrochemical
    0.32
     haircuts
    0.32
    POSITIVE LOGITS
    on
    0.42
     A
    0.41
    in
    0.39
    have
    0.39
    if
    0.38
    ká
    0.37
    K
    0.37
    ro
    0.37
    it
    0.37
     a
    0.36
    Act Density 1.095%

    No Known Activations