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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lawyers
    -0.07
    iyan
    -0.07
     theological
    -0.07
     VPN
    -0.07
     SpaceX
    -0.07
    chts
    -0.06
    ropolitan
    -0.06
    ути
    -0.06
    izr
    -0.06
     ftp
    -0.06
    POSITIVE LOGITS
     intrigue
    0.07
    .npy
    0.07
    "];↵↵
    0.06
    }↵
    0.06
    '%(
    0.06
    .SetText
    0.06
     Please
    0.06
     Shuffle
    0.06
    .*,
    0.06
    。不
    0.06
    Act Density 0.012%

    No Known Activations