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

    Neuronpedia

    INDEX
    Explanations

    actually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (firebase
    -0.09
     eighteenth
    -0.08
     empower
    -0.08
     advisory
    -0.08
    (Auth
    -0.08
    (console
    -0.08
     hygiene
    -0.08
     cia
    -0.08
    alerts
    -0.08
     slogan
    -0.08
    POSITIVE LOGITS
     suitable
    0.11
     chosen
    0.09
     suitably
    0.09
     conducive
    0.09
     Suitable
    0.09
     chose
    0.09
     convenient
    0.08
     Suit
    0.08
     planar
    0.08
     I'll
    0.08
    Act Density 0.056%

    No Known Activations