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

    Neuronpedia

    INDEX
    Explanations

    dynamics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Above
    -0.08
    (Location
    -0.07
     hệ
    -0.07
    /app
    -0.06
    wal
    -0.06
     Scaffold
    -0.06
     protestors
    -0.06
    ']}}</
    -0.06
    pre
    -0.06
    [input
    -0.06
    POSITIVE LOGITS
     dynamics
    0.31
     Dynamics
    0.25
    ynamics
    0.13
     freaking
    0.08
     gefunden
    0.07
     stamina
    0.07
     Genç
    0.07
    YNAM
    0.07
    discount
    0.07
    Damage
    0.07
    Act Density 0.006%

    No Known Activations