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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gom
    -0.08
     mature
    -0.08
    玲
    -0.08
     adorable
    -0.07
     clocks
    -0.07
    Saint
    -0.07
     wonderfully
    -0.07
     couples
    -0.07
     projects
    -0.07
     preschool
    -0.07
    POSITIVE LOGITS
    (Throwable
    0.10
     caused
    0.09
     verurs
    0.09
     strerror
    0.09
     причина
    0.09
     الإيط
    0.08
     veroorzaakt
    0.08
     verursacht
    0.08
     causado
    0.08
    .reason
    0.08
    Act Density 0.003%

    No Known Activations