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

    Neuronpedia

    INDEX
    Explanations

    card

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plasma
    -0.08
     мом
    -0.07
    -Israel
    -0.07
     Frankfurt
    -0.06
    (Character
    -0.06
     Encoding
    -0.06
     Snapshot
    -0.06
     Mutable
    -0.06
    ourn
    -0.06
    /block
    -0.06
    POSITIVE LOGITS
     loads
    0.07
    leccion
    0.06
     impr
    0.06
     Ви
    0.06
     ryb
    0.06
     adventures
    0.06
    isseur
    0.06
     Charg
    0.06
     conoc
    0.06
    เค
    0.06
    Act Density 0.004%

    No Known Activations