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

    Neuronpedia

    INDEX
    Explanations

    negative thoughts/emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defines
    -0.07
    ��
    -0.07
     competency
    -0.07
    doesn
    -0.07
    화를
    -0.07
    _blocked
    -0.06
    ision
    -0.06
    -wing
    -0.06
    нам
    -0.06
    portunity
    -0.06
    POSITIVE LOGITS
    Oper
    0.06
     Upgrade
    0.06
     sins
    0.06
    ."↵↵↵
    0.06
     prive
    0.06
    CONDS
    0.05
     duplic
    0.05
     συνέ
    0.05
    (User
    0.05
     nou
    0.05
    Act Density 0.034%

    No Known Activations