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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	format
    -0.07
     Abby
    -0.07
     eas
    -0.07
    'en
    -0.07
    奶
    -0.06
     ne
    -0.06
    다
    -0.06
     diarrhea
    -0.06
     Bra
    -0.06
    ’en
    -0.06
    POSITIVE LOGITS
     refl
    0.07
    snippet
    0.06
    ク
    0.06
     blazing
    0.06
    iciones
    0.06
     misunderstand
    0.06
     oppress
    0.06
    monds
    0.06
     влия
    0.06
    .addClass
    0.06
    Act Density 0.138%

    No Known Activations