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

    Neuronpedia

    INDEX
    Explanations

    geometry shapes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hive
    -0.07
    Swap
    -0.07
    _python
    -0.07
    Assigned
    -0.07
    Lua
    -0.06
    (QL
    -0.06
     Vermont
    -0.06
     Dodd
    -0.06
    Cel
    -0.06
     Gia
    -0.06
    POSITIVE LOGITS
    ّا
    0.06
    .constructor
    0.06
     potent
    0.06
    ;text
    0.06
    "><
    0.06
     مسئ
    0.06
     }↵↵↵↵↵↵
    0.06
     Protector
    0.06
     accountant
    0.05
    ;top
    0.05
    Act Density 0.044%

    No Known Activations