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

    Neuronpedia

    INDEX
    Explanations

    every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addir
    -0.07
    .detectChanges
    -0.07
    _loading
    -0.07
     detecting
    -0.07
     crank
    -0.07
    chematic
    -0.07
     vh
    -0.06
     loadImage
    -0.06
    $j
    -0.06
    (optional
    -0.06
    POSITIVE LOGITS
    EX
    0.08
    XXX
    0.07
    �
    0.07
    无忧
    0.07
    小于
    0.07
    OUR
    0.07
     akin
    0.06
    舒
    0.06
    辛苦
    0.06
    работ
    0.06
    Act Density 0.027%

    No Known Activations