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

    Neuronpedia

    INDEX
    Explanations

    family of 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     પ્રથમ
    0.50
    iguation
    0.50
     प्रथम
    0.48
     गठबंधन
    0.45
    acquisto
    0.45
     创建
    0.43
     શહેર
    0.42
    ayos
    0.42
     Созда
    0.41
     కొత్త
    0.41
    POSITIVE LOGITS
     tablets
    0.49
     appetite
    0.47
     confirms
    0.47
     links
    0.46
     ep
    0.46
     gebruiken
    0.46
     bruising
    0.45
     genes
    0.45
    ר
    0.44
     luck
    0.44
    Act Density 0.003%

    No Known Activations