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

    Neuronpedia

    INDEX
    Explanations

    division

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Args
    -0.07
     revived
    -0.07
     MLB
    -0.06
    博
    -0.06
    ��
    -0.06
    .wav
    -0.06
    olk
    -0.06
    ;


↵
    -0.06
     nipples
    -0.06
     pundits
    -0.06
    POSITIVE LOGITS
    ONSE
    0.07
    ()*
    0.07
    compileComponents
    0.06
    '))
↵
    0.06
    (st
    0.06
    .ศ
    0.06
     validation
    0.06
    itive
    0.06
    ={},
    0.06
     */
↵
    0.06
    Act Density 0.001%

    No Known Activations