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

    Neuronpedia

    INDEX
    Explanations

    country names or regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flatable
    0.49
    lens
    0.47
    <0xBC>
    0.43
    hai
    0.43
    học
    0.43
    life
    0.42
    lost
    0.41
    äns
    0.41
    moved
    0.41
    lated
    0.40
    POSITIVE LOGITS
    信用卡
    0.49
    TIP
    0.47
     אם
    0.46
    TLE
    0.46
     dakkh
    0.45
     pasada
    0.45
     atunci
    0.44
     wenn
    0.44
     ይህም
    0.44
     מ
    0.43
    Act Density 0.006%

    No Known Activations