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

    Neuronpedia

    INDEX
    Explanations

    Among

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .executor
    -0.07
     antig
    -0.07
     attacks
    -0.07
    UPDATED
    -0.07
    buttons
    -0.07
     GDK
    -0.06
     referral
    -0.06
     jejichž
    -0.06
    Criteria
    -0.06
     alliances
    -0.06
    POSITIVE LOGITS
    olog
    0.06
     Milit
    0.06
    艦
    0.06
     Narr
    0.06
    集
    0.06
    व
    0.06
     meine
    0.06
     lawful
    0.06
    Accessible
    0.05
    conto
    0.05
    Act Density 0.009%

    No Known Activations