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

    Neuronpedia

    INDEX
    Explanations

    content generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Upcoming
    0.56
    חים
    0.50
    ท
    0.50
    hut
    0.46
    Un
    0.46
    บร
    0.46
    Infrastructure
    0.45
    Update
    0.44
    acetic
    0.44
    lut
    0.44
    POSITIVE LOGITS
    وازي
    0.54
     ríg
    0.53
     possui
    0.47
     Nxe
    0.46
     samoz
    0.46
     veste
    0.44
     silvest
    0.44
     sogen
    0.43
     تركيب
    0.43
     действие
    0.42
    Act Density 0.001%

    No Known Activations