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

    Neuronpedia

    INDEX
    Explanations

    tool related to machine learning models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вме
    0.41
    狽
    0.39
    Um
    0.36
     Intell
    0.36
     UM
    0.36
     움
    0.35
     Strict
    0.35
     neck
    0.34
     சொல்
    0.34
     chấm
    0.34
    POSITIVE LOGITS
    Yak
    0.38
    Lok
    0.38
     Lap
    0.37
     Yak
    0.37
    kur
    0.36
    dam
    0.36
     Barn
    0.35
     dam
    0.34
     Burton
    0.34
    lagen
    0.34
    Act Density 0.013%

    No Known Activations