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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Packaging
    -0.07
     ngoài
    -0.07
     piss
    -0.07
    	ptr
    -0.07
     richTextBox
    -0.07
    汚
    -0.06
     ball
    -0.06
    Anal
    -0.06
    蓬勃
    -0.06
    桥梁
    -0.06
    POSITIVE LOGITS
    ,no
    0.07
    þ
    0.07
    acias
    0.07
    0.07
    �
    0.07
     yielded
    0.06
    天河
    0.06
    有用
    0.06
    boat
    0.06
    	hit
    0.06
    Act Density 0.017%

    No Known Activations