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

    Neuronpedia

    INDEX
    Explanations

    authorized JavaScript origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    デル
    0.36
    amatkan
    0.36
     चढ़ा
    0.35
    อร
    0.35
     ব্লগার
    0.35
    ทะ
    0.35
     לת
    0.34
     كري
    0.34
    wrapping
    0.34
    ковый
    0.34
    POSITIVE LOGITS
     Reserve
    0.35
     Kazakh
    0.34
     Rut
    0.33
     penalty
    0.33
     நான்கு
    0.33
     tier
    0.32
     money
    0.31
     duration
    0.31
    Reserve
    0.31
     requirements
    0.31
    Act Density 0.006%

    No Known Activations