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

    Neuronpedia

    INDEX
    Explanations

    postcolonial, than, Ghost, or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐌
    0.95
     muebles
    0.93
    ی
    0.89
    𝐖
    0.88
     afectada
    0.83
    𝙈
    0.82
    蹤
    0.82
    𝐼
    0.82
    𝐓
    0.81
    𝐎
    0.80
    POSITIVE LOGITS
     disamb
    0.70
     Un
    0.66
     Prak
    0.65
     flint
    0.65
     тэ
    0.64
    ды
    0.63
    ,
    0.63
     reps
    0.63
    বুদ্ধ
    0.63
     Eur
    0.62
    Act Density 0.005%

    No Known Activations