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

    Neuronpedia

    INDEX
    Explanations

    Designation Day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    1.55
    "',
    1.35
     держави
    1.32
    เจน
    1.30
    ')),
    1.29
     streaks
    1.27
    טת
    1.27
    硖
    1.26
    يه
    1.25
    <0xB8>
    1.24
    POSITIVE LOGITS
    ↵
    1.89
    veel
    1.84
    irla
    1.80
    ל
    1.78
    การ
    1.77
     hátsó
    1.76
    𝘪
    1.73
    वीं
    1.69
    Kya
    1.67
     médio
    1.59
    Act Density 0.000%

    No Known Activations