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

    Neuronpedia

    INDEX
    Explanations

    intake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utilizar
    -0.07
     policemen
    -0.06
    しない
    -0.06
    _npc
    -0.06
    >'
↵
    -0.06
    男人
    -0.06
     Vulcan
    -0.06
    [ch
    -0.06
     možnost
    -0.06
     Peygamber
    -0.06
    POSITIVE LOGITS
     intake
    0.08
    ти
    0.07
    DUCT
    0.06
    取
    0.06
     Keto
    0.06
    \Http
    0.06
    CI
    0.06
    crap
    0.06
     MCS
    0.06
     exceptionally
    0.06
    Act Density 0.002%

    No Known Activations