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

    Neuronpedia

    INDEX
    Explanations

    providing reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    盛り
    0.60
     वर्तमान
    0.59
    ตก
    0.59
     funcionamento
    0.57
     zeigt
    0.57
    ంచి
    0.57
    ত্ম
    0.57
     Needed
    0.57
    Utilities
    0.57
     যেখানে
    0.56
    POSITIVE LOGITS
     reasons
    4.81
     Reasons
    4.12
     reason
    4.06
    Reasons
    3.76
    reason
    3.35
     razones
    3.31
     raisons
    3.21
     Reason
    3.16
    理由
    3.10
     이유
    3.04
    Act Density 0.090%

    No Known Activations