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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doesnt
    -0.07
    籍
    -0.07
     implicated
    -0.07
     арх
    -0.06
    .mark
    -0.06
     novels
    -0.06
    -Pacific
    -0.06
     розрах
    -0.06
    �
    -0.06
    etypes
    -0.06
    POSITIVE LOGITS
    ortion
    0.07
    .xlim
    0.06
    Collider
    0.06
     تولید
    0.06
     Trung
    0.06
    (Arrays
    0.06
    Impl
    0.06
     fatalError
    0.06
     squeeze
    0.06
    -destruct
    0.05
    Act Density 0.000%

    No Known Activations