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

    Neuronpedia

    INDEX
    Explanations

    Crisis text line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ッツ
    0.41
    ときの
    0.41
    াস্থ্যের
    0.39
    ㄓ
    0.39
     ग्राहकों
    0.38
     atributos
    0.38
     КС
    0.38
     झालेले
    0.38
    दया
    0.38
     খেজুর
    0.38
    POSITIVE LOGITS
    submit
    0.59
     دریافت
    0.47
     ontvang
    0.47
    Submit
    0.47
    Receive
    0.46
     Submit
    0.46
     Receive
    0.46
    提交
    0.45
    receive
    0.43
     submit
    0.43
    Act Density 0.007%

    No Known Activations