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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gathered
    -0.07
     гри
    -0.06
    �
    -0.06
    abcdefghijklmnopqrstuvwxyz
    -0.06
    �
    -0.06
    antity
    -0.06
     Jihad
    -0.06
    .gpu
    -0.06
     innocence
    -0.06
    igor
    -0.06
    POSITIVE LOGITS
    =B
    0.06
    Aus
    0.06
    ีอย
    0.06
     VX
    0.06
     terrace
    0.06
    ```
    0.06
    _depart
    0.06
    767
    0.06
     cil
    0.06
     هست
    0.06
    Act Density 0.000%

    No Known Activations