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

    Neuronpedia

    INDEX
    Explanations

    `should join` "future"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isiä
    0.86
    デバイス
    0.85
     garante
    0.85
     automó
    0.83
     karenge
    0.83
    𝙻
    0.82
     declara
    0.82
     Ça
    0.82
    庀
    0.81
     тех
    0.80
    POSITIVE LOGITS
    ۥ
    0.80
    Pel
    0.75
    Rx
    0.74
    TES
    0.74
    Tes
    0.73
    Enhanced
    0.70
    🔥🔥
    0.70
    на
    0.68
    lon
    0.68
    Rows
    0.67
    Act Density 0.000%

    No Known Activations