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

    Neuronpedia

    INDEX
    Explanations

    Taylor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schwangerschaft
    -0.76
    ִּ
    -0.75
     במח
    -0.74
     THANKS
    -0.70
    Agregar
    -0.70
     Yesus
    -0.69
    Ʒ
    -0.68
     bạo
    -0.68
    chevron
    -0.68
    চ
    -0.66
    POSITIVE LOGITS
    Taylor
    0.82
    くらい
    0.80
    ≯
    0.80
    iens
    0.80
     niem
    0.79
     TAYLOR
    0.76
     Tay
    0.76
     taylor
    0.76
    ロナ
    0.75
    chaften
    0.75
    Act Density 0.016%

    No Known Activations