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

    Neuronpedia

    INDEX
    Explanations

    say quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ificates
    -0.07
    文化旅游
    -0.07
    �
    -0.06
    uspended
    -0.06
     позв
    -0.06
    诲
    -0.06
    体育在线
    -0.06
    累了
    -0.06
    ului
    -0.06
    .MediaType
    -0.06
    POSITIVE LOGITS
    みたいな
    0.07
     %↵↵
    0.07
     يبدو
    0.07
     reluctance
    0.07
    $tmp
    0.07
    енко
    0.07
    能看出
    0.07
     hề
    0.07
     ]];
    0.07
     SNP
    0.06
    Act Density 0.020%

    No Known Activations