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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    绲
    -0.07
     стали
    -0.07
     simulator
    -0.07
    Subscription
    -0.07
     propagated
    -0.06
    coords
    -0.06
     trắng
    -0.06
     soll
    -0.06
     groundwater
    -0.06
     möchte
    -0.06
    POSITIVE LOGITS
    riends
    0.08
    Wins
    0.07
    援助
    0.07
    many
    0.07
    友谊
    0.06
    GetInstance
    0.06
    היסטוריה
    0.06
    :^
    0.06
    МИ
    0.06
    谛
    0.06
    Act Density 0.005%

    No Known Activations