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

    Neuronpedia

    INDEX
    Explanations

    quoted speech followed by speaker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *:
    0.22
    :}
    0.22
     shortfall
    0.22
     అయితే
    0.21
    不足
    0.21
     ():
    0.20
    Questions
    0.20
     lave
    0.20
     bolas
    0.20
    ：
    0.20
    POSITIVE LOGITS
     referring
    0.23
    の声
    0.21
     이라고
    0.21
     supervising
    0.21
     कहकर
    0.20
    说着
    0.20
    uarine
    0.20
    enic
    0.20
    という
    0.19
     remarked
    0.19
    Act Density 0.193%

    No Known Activations