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

    Neuronpedia

    INDEX
    Explanations

    Foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Thrones
    -0.07
    .list
    -0.07
    ойно
    -0.06
    лась
    -0.06
    -strong
    -0.06
    ncia
    -0.06
     Streams
    -0.06
    기는
    -0.06
     срок
    -0.06
    POSITIVE LOGITS
    _SSL
    0.07
    .radius
    0.07
     دلار
    0.06
    ."},↵
    0.06
     TreeSet
    0.06
    Reverse
    0.06
     Sher
    0.05
     الجن
    0.05
    (touch
    0.05
     HEL
    0.05
    Act Density 0.045%

    No Known Activations