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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esidir
    -0.06
    あり
    -0.06
    授
    -0.06
    diğini
    -0.06
     παρά
    -0.06
    /aws
    -0.06
     encoding
    -0.06
     HT
    -0.06
    Helvetica
    -0.06
     проте
    -0.06
    POSITIVE LOGITS
    inish
    0.07
     Panic
    0.07
     mně
    0.06
    _hat
    0.06
    楼
    0.06
    _me
    0.06
    /power
    0.06
     stereotype
    0.06
    '],↵↵
    0.06
    ...
    0.06
    Act Density 0.048%

    No Known Activations