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

    Neuronpedia

    INDEX
    Explanations

    funding, investment, cost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pire
    1.43
    황
    1.36
     uniqu
    1.29
     unica
    1.28
     assignee
    1.27
     ld
    1.25
     organizada
    1.23
    ท่าน
    1.23
    嬲
    1.21
    válto
    1.20
    POSITIVE LOGITS
    offs
    1.91
    throat
    1.88
    knife
    1.67
    cuts
    1.65
     corners
    1.63
     razor
    1.61
     umbilical
    1.57
    剣
    1.50
     scraps
    1.48
    getline
    1.48
    Act Density 0.119%

    No Known Activations