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

    Neuronpedia

    INDEX
    Explanations

    There is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ベ
    0.41
    friend
    0.39
     brauchen
    0.38
    IsEnabled
    0.37
     داریم
    0.36
     eneste
    0.36
     there
    0.36
    There
    0.35
    Is
    0.35
    有什么
    0.35
    POSITIVE LOGITS
     तार
    0.42
    ሖ
    0.40
     Neu
    0.40
    ேஷ்
    0.40
     Weitere
    0.40
     Colombo
    0.40
     Als
    0.39
     Ν
    0.39
     μ
    0.39
     Ρ
    0.39
    Act Density 0.001%

    No Known Activations