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

    Neuronpedia

    INDEX
    Explanations

    Multi-Head Attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trio
    0.72
     integration
    0.67
     viewer
    0.64
    ینی
    0.64
     integrate
    0.64
     triangle
    0.63
     ойной
    0.63
     শুরু
    0.63
     bite
    0.61
     man
    0.61
    POSITIVE LOGITS
     Kunststoff
    0.84
    Funny
    0.82
     Rainbow
    0.81
     rainbows
    0.80
     showers
    0.76
    humidity
    0.76
    湿度
    0.75
     Funny
    0.75
    쨍
    0.74
     aquifers
    0.73
    Act Density 0.004%

    No Known Activations