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

    Neuronpedia

    INDEX
    Explanations

    questions or math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的确是
    -0.07
    有必要
    -0.07
     curled
    -0.07
    ことを
    -0.07
     стали
    -0.06
    ترة
    -0.06
     alarmed
    -0.06
    셑
    -0.06
     accurate
    -0.06
     직접
    -0.06
    POSITIVE LOGITS
    easy
    0.08
     explanatory
    0.07
     communications
    0.07
     leash
    0.07
    zt
    0.07
     Pal
    0.06
    Reminder
    0.06
    yyy
    0.06
     Oktober
    0.06
    领导小组
    0.06
    Act Density 0.023%

    No Known Activations