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

    Neuronpedia

    INDEX
    Explanations

    commercial services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,en
    -0.07
     annonce
    -0.06
    ])).
    -0.06
    /http
    -0.06
    iT
    -0.06
     инфек
    -0.06
    “.
    -0.06
    ".
    -0.06
    ्रथ
    -0.06
     Adler
    -0.06
    POSITIVE LOGITS
    resher
    0.07
     शब
    0.07
    	Integer
    0.07
    �
    0.06
    ภ
    0.06
    íveis
    0.06
    _SAMPLES
    0.06
    ังส
    0.06
    cciones
    0.06
     میزان
    0.06
    Act Density 0.003%

    No Known Activations