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

    Neuronpedia

    INDEX
    Explanations

    The number one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сли
    -0.07
    orgeous
    -0.07
     غیر
    -0.07
    раг
    -0.06
     多
    -0.06
    ，都
    -0.06
    ická
    -0.06
    äs
    -0.06
    .bat
    -0.06
    iclass
    -0.06
    POSITIVE LOGITS
     réalis
    0.07
    """↵↵↵
    0.07
    -door
    0.07
     usar
    0.06
    .lift
    0.06
     pursuant
    0.06
     rpm
    0.06
     CORPORATION
    0.06
    (df
    0.06
     tmpl
    0.06
    Act Density 0.035%

    No Known Activations