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

    Neuronpedia

    INDEX
    Explanations

    foreign words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.45
    adora
    0.44
    图标
    0.43
    ora
    0.42
    eti
    0.41
    jecha
    0.41
    1
    0.41
    asta
    0.41
    eta
    0.40
     gave
    0.40
    POSITIVE LOGITS
     മറ്റു
    0.46
     হয়ত
    0.45
     belki
    0.45
    تن
    0.42
     হয়ত
    0.42
     turkeys
    0.41
     dagar
    0.40
     voire
    0.40
     andet
    0.40
    忔
    0.40
    Act Density 0.007%

    No Known Activations