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

    Neuronpedia

    INDEX
    Explanations

    single family property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ܆
    -1.91
    </b>
    -1.65
    箆
    -1.63
    屨
    -1.53
    idk
    -1.52
    -1.52
     издания
    -1.52
     captivating
    -1.51
    they
    -1.50
    ∵
    -1.48
    POSITIVE LOGITS
    This
    1.98
     Both
    1.64
     These
    1.63
     Those
    1.62
     этого
    1.60
    These
    1.59
     Here
    1.55
     kerap
    1.55
     this
    1.52
    larınız
    1.48
    Act Density 0.011%

    No Known Activations