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

    Neuronpedia

    INDEX
    Explanations

    building

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    缨
    0.69
    产生
    0.67
    ocere
    0.64
    产生的
    0.63
    শরণ
    0.62
    etição
    0.62
    oxygenase
    0.61
    洒
    0.61
    rierung
    0.57
    itochond
    0.57
    POSITIVE LOGITS
     build
    5.37
    Build
    5.21
     Build
    5.17
    build
    5.15
     builds
    5.07
     building
    4.99
    Building
    4.67
     Building
    4.66
     Builds
    4.63
    building
    4.60
    Act Density 1.650%

    No Known Activations