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

    Neuronpedia

    INDEX
    Explanations

    separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Doug
    -0.06
    	max
    -0.06
     Trang
    -0.06
     �
    -0.06
    模型
    -0.06
     }),
    -0.06
    foobar
    -0.06
    .Mockito
    -0.06
    ="../
    -0.06
     ttl
    -0.06
    POSITIVE LOGITS
     squeez
    0.07
    pon
    0.07
    णन
    0.07
     Орг
    0.06
     "
    0.06
     собира
    0.06
    !
    0.06
     facing
    0.06
    POSITION
    0.06
    oled
    0.06
    Act Density 0.002%

    No Known Activations