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
    isman
    -0.07
     favourites
    -0.07
    des
    -0.06
    洗礼
    -0.06
    permit
    -0.06
    ANK
    -0.06
    :UIControlStateNormal
    -0.06
    导读
    -0.06
    _INV
    -0.06
     explanatory
    -0.06
    POSITIVE LOGITS
    设施建设
    0.07
    .stream
    0.07
    尽早
    0.07
     complic
    0.07
    能夠
    0.07
    вер
    0.07
     {

↵
    0.07
     gadgets
    0.07
     `"
    0.06
    ᩁ
    0.06
    Act Density 0.001%

    No Known Activations