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

    Neuronpedia

    INDEX
    Explanations

    names and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存档备份
    0.34
    চন্দ্রের
    0.33
    ឧបករណ៍
    0.31
    䒑
    0.31
    льные
    0.31
    ческую
    0.30
    лькі
    0.30
    मीत
    0.30
    ॉग
    0.30
     २००
    0.30
    POSITIVE LOGITS
    ":
    0.29
     ..."
    0.29
    ':
    0.26
    ior
    0.26
    >((
    0.25
    arik
    0.25
    ';
    0.25
    ui
    0.24
     ."
    0.24
    ?’”
    0.24
    Act Density 0.683%

    No Known Activations