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

    Neuronpedia

    INDEX
    Explanations

    one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     واحد
    0.36
     واحدة
    0.36
     hour
    0.35
    เดียว
    0.35
     jedin
    0.34
    Single
    0.34
     다른
    0.33
     ఒక్క
    0.33
     hoặc
    0.33
    或者是
    0.33
    POSITIVE LOGITS
     particularly
    0.44
     particolarmente
    0.41
     cannot
    0.36
     particularmente
    0.35
    particularly
    0.35
     частности
    0.34
    部分は
    0.33
     analysis
    0.32
     such
    0.32
    部分
    0.31
    Act Density 0.011%

    No Known Activations