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

    Neuronpedia

    INDEX
    Explanations

    option lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মূলক
    0.35
    相关的
    0.33
     Issues
    0.33
     Policy
    0.33
    Issues
    0.32
    Music
    0.31
    μών
    0.31
     Miao
    0.31
     Shore
    0.31
     Wars
    0.31
    POSITIVE LOGITS
     sintomas
    0.38
     endast
    0.37
     concave
    0.36
     ہے
    0.35
     ਹੈ
    0.33
     terdapat
    0.32
     symmet
    0.32
     limpeza
    0.32
    リューム
    0.32
     sympt
    0.31
    Act Density 0.050%

    No Known Activations