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

    Neuronpedia

    INDEX
    Explanations

    text fragments and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stricken
    0.73
    getC
    0.72
     chết
    0.71
    ᕕ
    0.71
    𝑻
    0.67
    strict
    0.66
    选项
    0.66
    ⴷ
    0.66
    时期
    0.65
     роки
    0.65
    POSITIVE LOGITS
     hormones
    0.87
     railways
    0.84
    های
    0.83
     feud
    0.80
    ۔
    0.80
    ал
    0.80
    ių
    0.80
    ្សែ
    0.80
     boutiques
    0.80
     cultivator
    0.79
    Act Density 0.000%

    No Known Activations