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

    Neuronpedia

    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     техні
    -0.07
    �
    -0.07
    Nano
    -0.07
    Dir
    -0.07
    ισμός
    -0.07
    ентами
    -0.06
     drilled
    -0.06
    .copyOf
    -0.06
    USED
    -0.06
    Sender
    -0.06
    POSITIVE LOGITS
     ड
    0.07
    ;c
    0.06
     fen
    0.06
    _gs
    0.06
    ंक
    0.06
     CARE
    0.06
    .prev
    0.06
    :'',
    0.06
    ++++++++++++++++
    0.06
    -remove
    0.06
    Act Density 0.064%

    No Known Activations