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

    Neuronpedia

    INDEX
    Explanations

    conversation excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cyn
    -0.08
    rend
    -0.07
    .default
    -0.06
    𝗻
    -0.06
    .runner
    -0.06
    見
    -0.06
    流星
    -0.06
    啶
    -0.06
    	scene
    -0.06
    嬥
    -0.06
    POSITIVE LOGITS
    success
    0.07
    ware
    0.06
    chs
    0.06
    但是他
    0.06
    ורות
    0.06
    orage
    0.06
     bunch
    0.06
     ثلاثة
    0.06
    凭着
    0.06
    rikes
    0.06
    Act Density 0.022%

    No Known Activations