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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pound
    -0.07
     ni
    -0.06
     ipv
    -0.06
     interess
    -0.06
    oir
    -0.06
    �
    -0.06
    Wei
    -0.06
     هل
    -0.06
     teamwork
    -0.06
     Martial
    -0.06
    POSITIVE LOGITS
     Genuine
    0.06
     }
↵
↵
↵
↵
    0.06
    electric
    0.06
     ownerId
    0.06
    ارة
    0.06
     consuming
    0.06
     paranormal
    0.06
    ’une
    0.06
     doc
    0.06
     naj
    0.06
    Act Density 0.175%

    No Known Activations