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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    显示
    -0.08
    -0.07
    �
    -0.07
     watering
    -0.06
    舞
    -0.06
     중심
    -0.06
    :\\
    -0.06
    .bio
    -0.06
    concat
    -0.06
     Hero
    -0.06
    POSITIVE LOGITS
    ategor
    0.07
    Hong
    0.07
    belie
    0.06
    RAND
    0.06
    egasus
    0.06
     Perl
    0.06
     APA
    0.06
    .Ver
    0.06
     UserRepository
    0.06
    _MSB
    0.06
    Act Density 0.026%

    No Known Activations