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

    Neuronpedia

    INDEX
    Explanations

    jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (JS
    -0.07
     provisioning
    -0.07
     Пот
    -0.07
     phủ
    -0.06
     Kara
    -0.06
     زیر
    -0.06
     giảng
    -0.06
     distrust
    -0.06
     laundering
    -0.06
    (commit
    -0.06
    POSITIVE LOGITS
     Interested
    0.07
    /todo
    0.07
    Ignoring
    0.06
     �
    0.06
     unmistak
    0.06
     StringField
    0.06
    ArrayOf
    0.06
    special
    0.06
    akest
    0.06
     getContentPane
    0.06
    Act Density 0.021%

    No Known Activations