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

    Neuronpedia

    INDEX
    Explanations

    Humor and comedy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FileOutputStream
    -0.08
    oxide
    -0.07
     deadliest
    -0.07
    mai
    -0.07
    allocate
    -0.07
    比起
    -0.07
    =start
    -0.07
     convenient
    -0.07
     Cult
    -0.06
     vacc
    -0.06
    POSITIVE LOGITS
    حط
    0.08
    $a
    0.07
    月亮
    0.07
     projects
    0.06
    خر
    0.06
    ictim
    0.06
    IFn
    0.06
     Activity
    0.06
    힐
    0.06
    NAL
    0.06
    Act Density 0.221%

    No Known Activations