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

    Neuronpedia

    INDEX
    Explanations

    four

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teas
    -0.07
    ensis
    -0.07
    산
    -0.07
    participants
    -0.07
     env
    -0.07
    urg
    -0.07
     losses
    -0.06
    _prog
    -0.06
     spam
    -0.06
    组织开展
    -0.06
    POSITIVE LOGITS
    훤
    0.09
    _Menu
    0.07
    屃
    0.07
    阎
    0.07
    שיחה
    0.07
    咉
    0.06
     objected
    0.06
     rubbed
    0.06
    _Construct
    0.06
    儘
    0.06
    Act Density 0.003%

    No Known Activations