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

    Neuronpedia

    INDEX
    Explanations

    Explanation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    שלם
    -0.08
    泄
    -0.08
     Gregory
    -0.08
     Peek
    -0.07
    :'#
    -0.07
     clearing
    -0.07
     distinctly
    -0.07
    ערים
    -0.07
    镶嵌
    -0.07
    .mark
    -0.07
    POSITIVE LOGITS
    PM
    0.07
    꼴
    0.06
    	time
    0.06
     novembre
    0.06
     boyfriend
    0.06
     family
    0.06
    .social
    0.06
     job
    0.06
    -datepicker
    0.06
     Level
    0.06
    Act Density 0.011%

    No Known Activations