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

    Neuronpedia

    INDEX
    Explanations

    Legal citations/references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sensitive
    -0.07
     hoped
    -0.07
     представ
    -0.07
     Chad
    -0.07
     exploited
    -0.07
     Demand
    -0.07
    钍
    -0.06
     pouring
    -0.06
     Sed
    -0.06
     Pag
    -0.06
    POSITIVE LOGITS
     punishable
    0.07
     liberties
    0.06
     clinics
    0.06
     les
    0.06
    老师
    0.06
    高于
    0.06
    וא
    0.06
     ratios
    0.06
    锜
    0.06
    digits
    0.06
    Act Density 0.006%

    No Known Activations