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
     boredom
    -0.07
    _EXTRA
    -0.07
    _PLACE
    -0.06
     небольш
    -0.06
     αφ
    -0.06
    _ord
    -0.06
    stacles
    -0.06
    odo
    -0.06
    boBox
    -0.06
    auge
    -0.06
    POSITIVE LOGITS
     Steph
    0.07
    >Contact
    0.07
    _DATABASE
    0.06
     зовсім
    0.06
    ían
    0.06
    quiring
    0.06
     إليه
    0.06
    ��
    0.06
    dictionary
    0.06
    iously
    0.06
    Act Density 0.006%

    No Known Activations