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

    Neuronpedia

    INDEX
    Explanations

    Google Cloud API code (or similar)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拿出来
    -0.07
    [rand
    -0.07
    .addListener
    -0.07
    -collar
    -0.07
    ší
    -0.07
     cherish
    -0.07
    .Raise
    -0.07
    yyval
    -0.07
    常用的
    -0.07
    航母
    -0.07
    POSITIVE LOGITS
    �
    0.07
    								↵
    0.07
    _adc
    0.07
    (segment
    0.07
    examples
    0.07
    utters
    0.07
    驳
    0.07
    JC
    0.07
    راق
    0.06
    ams
    0.06
    Act Density 0.000%

    No Known Activations