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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cknowled
    -0.09
     emitted
    -0.08
    Presence
    -0.08
     прошлого
    -0.07
     pretrained
    -0.07
    altres
    -0.07
     dz
    -0.07
    Assim
    -0.07
     transmitted
    -0.07
     prevail
    -0.07
    POSITIVE LOGITS
    是一
    0.10
     называ
    0.09
     termed
    0.09
    所谓
    0.09
    稱
    0.08
     ahaan
    0.08
     dubbed
    0.08
     называется
    0.08
     cute
    0.08
     gọi
    0.08
    Act Density 0.014%

    No Known Activations