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

    Neuronpedia

    INDEX
    Explanations

    else

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pfizer
    -0.07
    評
    -0.06
     ecl
    -0.06
    ใหม
    -0.06
     良
    -0.06
     PAS
    -0.06
    _queues
    -0.06
    cou
    -0.06
    .Maximum
    -0.06
    /stretchr
    -0.06
    POSITIVE LOGITS
    �权
    0.06
     Consult
    0.06
     retain
    0.06
    身份
    0.06
     ambitions
    0.06
     upload
    0.06
     Thurs
    0.05
    entr
    0.05
    ENOMEM
    0.05
     목소
    0.05
    Act Density 0.004%

    No Known Activations