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

    Neuronpedia

    INDEX
    Explanations

    random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ąż
    -0.07
    ';";↵
    -0.07
    because
    -0.06
     inch
    -0.06
    Daniel
    -0.06
     truth
    -0.06
    Unless
    -0.06
     }],↵
    -0.06
    	aux
    -0.06
     Національ
    -0.06
    POSITIVE LOGITS
    _int
    0.07
    USTOM
    0.06
     MOD
    0.06
    ypes
    0.06
    icks
    0.06
     Cod
    0.06
     Nationals
    0.06
     Consultants
    0.06
    <Integer
    0.06
     MLP
    0.06
    Act Density 0.000%

    No Known Activations