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

    Neuronpedia

    INDEX
    Explanations

    list of numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ievers
    0.41
     వారు
    0.40
     lique
    0.39
    ství
    0.38
     lettere
    0.37
     writs
    0.37
     Lett
    0.36
    awie
    0.36
     naziv
    0.36
    ietro
    0.35
    POSITIVE LOGITS
     subgraph
    0.47
    Subgraph
    0.45
    quear
    0.44
    Dataset
    0.44
    ๊ก
    0.44
    не
    0.43
     トート
    0.42
     optimisation
    0.42
    kuje
    0.42
    孅
    0.41
    Act Density 0.013%

    No Known Activations