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

    Neuronpedia

    INDEX
    Explanations

    string type argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    1.10
    ل
    1.08
    el
    1.06
    न
    0.85
    اط
    0.82
    ässig
    0.82
    ounding
    0.81
    দের
    0.80
    et
    0.80
    yce
    0.80
    POSITIVE LOGITS
    𝑒
    0.90
    𝑂
    0.87
    蔓
    0.84
     ric
    0.83
    ｨ
    0.82
     motorized
    0.82
     pembahasan
    0.82
    𝒃
    0.80
     berlaku
    0.80
     capitalize
    0.79
    Act Density 0.296%

    No Known Activations