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

    Neuronpedia

    INDEX
    Explanations

    location names and types of materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cleaning
    0.51
     painters
    0.48
     cleaning
    0.47
    omone
    0.46
     】
    0.46
     Trip
    0.44
    命中
    0.44
    \...
    0.44
     trip
    0.43
     Sponsored
    0.42
    POSITIVE LOGITS
    ین
    0.51
    confusion
    0.50
    ন
    0.47
     группе
    0.46
    ਕ
    0.45
    කො
    0.45
    સ
    0.44
    перед
    0.44
    ن
    0.44
    ก
    0.44
    Act Density 0.003%

    No Known Activations