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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upside
    -0.06
    108
    -0.06
     آمده
    -0.06
     paranoia
    -0.06
     Ambassador
    -0.06
    ประเทศไทย
    -0.06
    ("")]↵
    -0.06
     противоп
    -0.06
     darkest
    -0.06
    тиров
    -0.06
    POSITIVE LOGITS
    -key
    0.07
    (cor
    0.07
     документ
    0.07
    Computed
    0.07
    pa
    0.07
    /Core
    0.06
    reduce
    0.06
    -unused
    0.06
    HQ
    0.06
     Üy
    0.06
    Act Density 0.000%

    No Known Activations