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

    Neuronpedia

    INDEX
    Explanations

    salvage, salvation, salutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oshape
    0.38
    ógico
    0.38
    Px
    0.38
    섹
    0.38
    瞻
    0.37
    Ren
    0.37
    记得
    0.37
    枨
    0.37
    ֩
    0.37
    周知
    0.37
    POSITIVE LOGITS
     sal
    1.02
     SAL
    0.98
    sal
    0.88
    Sal
    0.87
    SAL
    0.86
     sali
    0.84
     Sal
    0.80
     saline
    0.75
     Salinas
    0.72
     salivary
    0.72
    Act Density 0.021%

    No Known Activations