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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itez
    -0.08
    ammad
    -0.07
     reconnect
    -0.07
     engulf
    -0.07
     credible
    -0.07
     sanitized
    -0.07
     articulate
    -0.07
    	resolve
    -0.07
     культу
    -0.07
     migrant
    -0.07
    POSITIVE LOGITS
    万台
    0.07
    codes
    0.07
    .setColumns
    0.07
    ”。↵↵
    0.07
     booth
    0.07
    ممار
    0.07
    Slots
    0.07
    䴥
    0.06
    ){
↵
↵
    0.06
    什麼
    0.06
    Act Density 0.014%

    No Known Activations