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

    Neuronpedia

    INDEX
    Explanations

    animal size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Besides
    -0.08
    preneur
    -0.07
     Problem
    -0.07
    positor
    -0.07
    ┽
    -0.07
    漳
    -0.07
     fug
    -0.07
     Provides
    -0.07
    [state
    -0.06
     самого
    -0.06
    POSITIVE LOGITS
    Как
    0.07
    䲟
    0.07
     ));
↵
    0.07
    ))}↵
    0.07
    太太
    0.06
    "])
↵
    0.06
    ⁻
    0.06
    戴着
    0.06
    URLConnection
    0.06
    都會
    0.06
    Act Density 0.010%

    No Known Activations