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

    Neuronpedia

    INDEX
    Explanations

    Massive Attack, PS5, figure, Particle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.70
    ip
    0.58
    ron
    0.57
    ety
    0.56
    ly
    0.55
    iv
    0.52
    ry
    0.51
    t
    0.50
    ir
    0.50
    r
    0.50
    POSITIVE LOGITS
    0.55
    ים
    0.50
    čili
    0.48
    逘
    0.47
     Muitos
    0.47
    获
    0.47
     máme
    0.46
    뒹
    0.46
    历史
    0.45
    0.45
    Act Density 0.001%

    No Known Activations