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

    Neuronpedia

    INDEX
    Explanations

    aim

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的带领
    -0.08
     feder
    -0.07
    后面的
    -0.07
    ates
    -0.07
     rencontre
    -0.07
     funkc
    -0.07
    OfBirth
    -0.07
    ViewState
    -0.07
     PayPal
    -0.06
    _dt
    -0.06
    POSITIVE LOGITS
    剿
    0.08
    捌
    0.07
    ꧈
    0.07
     X
    0.07
    烟囱
    0.07
     keyed
    0.06
    submission
    0.06
    搞
    0.06
    倪
    0.06
    槚
    0.06
    Act Density 0.018%

    No Known Activations