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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appointed
    -0.07
    Levels
    -0.07
    please
    -0.06
     Thanks
    -0.06
    **:
    -0.06
    ALE
    -0.06
     بانک
    -0.06
     although
    -0.06
    _PO
    -0.06
    ombo
    -0.06
    POSITIVE LOGITS
    �
    0.07
    yt
    0.07
     aplik
    0.07
    

↵
    0.06
    child
    0.06
    riz
    0.06
     PictureBox
    0.06
     Microsystems
    0.06
     Dise
    0.06
    ++++
    0.06
    Act Density 0.131%

    No Known Activations