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

    Neuronpedia

    INDEX
    Explanations

    say "team" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    469
    -0.07
    mono
    -0.07
    _BINDING
    -0.07
     člán
    -0.07
    ρίας
    -0.07
     swept
    -0.06
    團
    -0.06
     greedy
    -0.06
    \Repository
    -0.06
    */,↵
    -0.06
    POSITIVE LOGITS
    (UINT
    0.07
    ВС
    0.06
     SingleChildScrollView
    0.06
    íc
    0.06
     timeouts
    0.06
     Playstation
    0.06
     seiz
    0.06
     Danny
    0.06
     Χ
    0.06
     erb
    0.06
    Act Density 0.084%

    No Known Activations