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

    Neuronpedia

    INDEX
    Explanations

    customer feedback and product improvement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dialogue
    -0.06
    rejected
    -0.06
    ernel
    -0.06
    fav
    -0.06
    POSITORY
    -0.06
     Attack
    -0.06
    ruise
    -0.06
     linspace
    -0.06
    ฤษภาคม
    -0.06
    oters
    -0.06
    POSITIVE LOGITS
    Summon
    0.07
    ,L
    0.07
     pissed
    0.06
    内
    0.06
     wins
    0.06
    ريل
    0.06
    ье
    0.06
     flawless
    0.06
    _emails
    0.06
    ,C
    0.06
    Act Density 0.310%

    No Known Activations