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

    Neuronpedia

    INDEX
    Explanations

    go into, beyond, through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    петров
    0.29
    呼
    0.28
    calling
    0.28
     الند
    0.28
     परहेज
    0.28
     Vestone
    0.27
     destinée
    0.27
    履行
    0.26
     Petersburg
    0.26
    Calling
    0.26
    POSITIVE LOGITS
     wildcard
    0.34
     thematic
    0.30
     back
    0.30
    ambahkan
    0.29
     faucet
    0.28
     ternary
    0.28
     procede
    0.28
     buy
    0.28
     dimension
    0.27
     cruc
    0.27
    Act Density 0.011%

    No Known Activations