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

    Neuronpedia

    INDEX
    Explanations

    encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Values
    -0.06
     comenz
    -0.06
    columns
    -0.06
    책
    -0.06
    'post
    -0.06
    _bbox
    -0.06
    очку
    -0.06
    列表
    -0.06
     sparing
    -0.06
     Alien
    -0.06
    POSITIVE LOGITS
    	kfree
    0.07
    .Right
    0.06
     JNIEnv
    0.06
    _rhs
    0.06
    (GL
    0.06
     tụ
    0.06
    nor
    0.06
    GREEN
    0.06
    kills
    0.06
     FAILURE
    0.06
    Act Density 0.000%

    No Known Activations