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

    Neuronpedia

    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bots
    -0.07
    休
    -0.07
    <n
    -0.06
     separates
    -0.06
     highlight
    -0.06
    تون
    -0.06
     надо
    -0.06
    .getElementById
    -0.06
    лем
    -0.06
    uke
    -0.05
    POSITIVE LOGITS
     content
    0.09
     contenido
    0.07
     Content
    0.07
    区域
    0.07
     içeri
    0.07
    deliver
    0.07
    payload
    0.07
    filled
    0.07
     Scient
    0.07
    		
↵
↵
    0.07
    Act Density 0.026%

    No Known Activations