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

    Neuronpedia

    INDEX
    Explanations

    Tbill, H2O, MWD, Svelte, NWP, QEMU, HITS, c#, GPT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     》
    0.20
    腖
    0.20
     Į
    0.19
    䒷
    0.19
    のも
    0.19
     Publications
    0.18
     ©
    0.18
    妑
    0.18
     Fot
    0.18
     nace
    0.18
    POSITIVE LOGITS
     sklearn
    0.24
     GPT
    0.24
    python
    0.23
    GPT
    0.23
    FW
    0.23
     ChatGPT
    0.22
    sklearn
    0.22
     linguagem
    0.22
    fw
    0.22
    ChatGPT
    0.21
    Act Density 0.153%

    No Known Activations