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

    Neuronpedia

    INDEX
    Explanations

    Expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noticeably
    -0.07
    _ROOT
    -0.07
    าก
    -0.07
     Brah
    -0.07
    ृ
    -0.07
    .Mask
    -0.07
    んだ
    -0.07
     Appearance
    -0.07
    ши
    -0.06
    ancybox
    -0.06
    POSITIVE LOGITS
     đứ
    0.06
     promote
    0.06
     Marina
    0.06
     farming
    0.06
    (prod
    0.06
     overturn
    0.06
     také
    0.06
     Boise
    0.05
    �
    0.05
    PIC
    0.05
    Act Density 0.006%

    No Known Activations