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

    Neuronpedia

    INDEX
    Explanations

    Egypt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     behaved
    -0.06
     Manip
    -0.06
     ding
    -0.06
     FN
    -0.06
    Hat
    -0.06
     MQ
    -0.06
     Hat
    -0.06
    _group
    -0.06
    Talk
    -0.06
     произош
    -0.06
    POSITIVE LOGITS
     awakeFromNib
    0.07
     imposs
    0.06
    стров
    0.06
    /cpp
    0.06
    .priority
    0.06
     leo
    0.06
     tolerant
    0.06
     заним
    0.06
     pró
    0.06
    agent
    0.06
    Act Density 0.004%

    No Known Activations