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

    Neuronpedia

    INDEX
    Explanations

    describing or completing a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    followfollow
    0.45
     hr
    0.36
    꽉
    0.35
     kindly
    0.35
    iodo
    0.35
    GetInt
    0.34
     Cp
    0.34
    Nano
    0.34
    erai
    0.34
     دعوت
    0.34
    POSITIVE LOGITS
    續
    0.41
     ഒരാ
    0.40
    ïs
    0.38
    袁
    0.37
     física
    0.37
     möj
    0.37
     сможет
    0.37
     Tujuan
    0.37
     источ
    0.36
     idioma
    0.36
    Act Density 0.000%

    No Known Activations