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

    Neuronpedia

    INDEX
    Explanations

    numbered lists or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brooke
    1.04
    Aside
    1.02
    ﺀ
    0.99
     marie
    0.99
     Meadows
    0.98
     dutch
    0.97
     française
    0.97
     joe
    0.96
     recursive
    0.95
    пол
    0.95
    POSITIVE LOGITS
    imagen
    0.93
    itud
    0.89
     Lecture
    0.87
    ni
    0.87
     inscrito
    0.85
     காலம்
    0.85
    的花
    0.83
    聋
    0.83
     Надо
    0.81
    schaft
    0.80
    Act Density 0.080%

    No Known Activations