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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    э
    -0.07
    💠
    -0.07
     consolid
    -0.07
    APTER
    -0.07
     determines
    -0.07
     capsule
    -0.07
    ເ
    -0.06
    Axes
    -0.06
     hod
    -0.06
     Э
    -0.06
    POSITIVE LOGITS
    SSH
    0.07
    喜歡
    0.07
     Blank
    0.07
    𫢸
    0.06
    我们在
    0.06
    SOAP
    0.06
    ская
    0.06
    过多
    0.06
    ่น
    0.06
    SEA
    0.06
    Act Density 0.001%

    No Known Activations