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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical Discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ical
    -0.06
     South
    -0.06
    .visual
    -0.06
     мор
    -0.06
    .rc
    -0.06
     fadeIn
    -0.06
     Dün
    -0.06
     suffers
    -0.06
    :`~
    -0.06
    _cases
    -0.06
    POSITIVE LOGITS
     которую
    0.07
     تمام
    0.07
    arris
    0.06
    Arg
    0.06
    Love
    0.06
    (arc
    0.06
     haven
    0.06
    arking
    0.06
     القد
    0.06
    )[-
    0.06
    Act Density 0.001%

    No Known Activations