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

    Neuronpedia

    INDEX
    Explanations

    Paid ads and promotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الز
    0.42
    secure
    0.42
    Secure
    0.41
     $\
    0.41
     software
    0.40
    MW
    0.40
    Proxy
    0.39
    体
    0.39
     temer
    0.39
     ${
    0.39
    POSITIVE LOGITS
    ເ
    0.51
    Ნ
    0.47
    ៖
    0.47
    larım
    0.47
    ້
    0.46
    ຣ
    0.45
    țională
    0.45
     ionized
    0.44
    oureux
    0.44
    Clic
    0.44
    Act Density 0.000%

    No Known Activations