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

    Neuronpedia

    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ılık
    -0.09
    床
    -0.08
    amping
    -0.08
     Vir
    -0.07
    _channel
    -0.07
     Unternehmens
    -0.07
    排行榜
    -0.07
    汤
    -0.07
     Ability
    -0.07
    प्रिय
    -0.07
    POSITIVE LOGITS
     trajectory
    0.11
     trajectories
    0.10
     lived
    0.10
     tumult
    0.10
     affairs
    0.09
     intertwined
    0.09
    Trajectory
    0.09
     livelihood
    0.08
     ജീവിത
    0.08
    trajectory
    0.08
    Act Density 0.029%

    No Known Activations