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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pierws
    -0.07
    ensitive
    -0.07
     очеред
    -0.07
    genesis
    -0.06
    �
    -0.06
     SEG
    -0.06
     своей
    -0.06
     CE
    -0.06
    EntryPoint
    -0.06
     À
    -0.06
    POSITIVE LOGITS
     ****************************************************************
    0.07
    Jake
    0.07
    smtp
    0.06
    sf
    0.06
    '");↵
    0.06
     ************************
    0.06
    .pictureBox
    0.06
     sword
    0.06
     Timestamp
    0.06
    .dk
    0.06
    Act Density 0.002%

    No Known Activations