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

    Neuronpedia

    INDEX
    Explanations

    go

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ursal
    -0.07
     Releases
    -0.06
    OpenHelper
    -0.06
    ými
    -0.06
    posable
    -0.06
    xCC
    -0.06
     Telerik
    -0.06
     avocado
    -0.06
     arasındaki
    -0.06
     Narc
    -0.06
    POSITIVE LOGITS
    φαρ
    0.07
    nor
    0.07
     вис
    0.07
     Swarm
    0.07
     pige
    0.07
    ΟΤ
    0.07
     idi
    0.07
    İş
    0.06
    ibr
    0.06
    _aff
    0.06
    Act Density 0.009%

    No Known Activations