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

    Neuronpedia

    INDEX
    Explanations

    Chandigarh, master, Enough, Springs, Classic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    2.29
    िक
    2.07
    ن
    1.74
    on
    1.66
    и
    1.63
    n
    1.56
    ig
    1.54
    igkeit
    1.51
    та
    1.49
    е
    1.48
    POSITIVE LOGITS
    𝒓
    1.88
     erotic
    1.80
    强制
    1.74
    𝘈
    1.70
    澳
    1.68
    现代化
    1.67
    ουλ
    1.65
    durationType
    1.64
     electrophoresis
    1.64
    𝘢
    1.63
    Act Density 0.001%

    No Known Activations