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

    Neuronpedia

    INDEX
    Explanations

    previously published

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    904
    -0.07
    724
    -0.06
    신청
    -0.06
    ущ
    -0.06
    514
    -0.06
    541
    -0.06
    534
    -0.06
    610
    -0.06
    799
    -0.06
    cec
    -0.06
    POSITIVE LOGITS
     acidic
    0.07
     Against
    0.07
     Alexis
    0.06
    днання
    0.06
     A
    0.06
    /history
    0.06
     Improved
    0.06
     packets
    0.06
     ListTile
    0.06
     chapter
    0.06
    Act Density 0.041%

    No Known Activations