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

    Neuronpedia

    INDEX
    Explanations

    in conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iest
    0.22
    AN
    0.21
     That
    0.21
    .”
    0.20
    。
    0.20
    grave
    0.19
     inclinations
    0.19
     begann
    0.19
     commandments
    0.19
    М
    0.19
    POSITIVE LOGITS
    舴
    0.23
    牰
    0.22
     Wetlands
    0.22
    㗊
    0.22
    沚
    0.22
    வற்ற
    0.21
    由于
    0.21
    水量
    0.21
    流程
    0.21
    樘
    0.21
    Act Density 0.000%

    No Known Activations