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

    Neuronpedia

    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interchangeable
    -0.07
    Las
    -0.07
     Costco
    -0.06
     Sprite
    -0.06
     Normally
    -0.06
     또는
    -0.06
    ujte
    -0.06
    Normally
    -0.06
    _reference
    -0.06
     nikdo
    -0.06
    POSITIVE LOGITS
    EVENT
    0.09
    bound
    0.07
    認
    0.07
    passes
    0.07
    =min
    0.07
     patched
    0.07
    ?[
    0.07
     dedication
    0.07
    爆
    0.07
    ――――
    0.06
    Act Density 0.005%

    No Known Activations