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

    Neuronpedia

    INDEX
    Explanations

    х

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    omb
    -0.07
    老兵
    -0.07
     OnClickListener
    -0.07
    ㎤
    -0.07
    冰淇
    -0.07
    	cont
    -0.06
    ︺
    -0.06
     officer
    -0.06
    aming
    -0.06
    暑期
    -0.06
    POSITIVE LOGITS
     reversed
    0.08
     privately
    0.07
    nç
    0.07
     fixtures
    0.07
    千方百
    0.07
     אחרת
    0.07
     х
    0.07
     apprent
    0.07
     wealthy
    0.07
     Approval
    0.07
    Act Density 0.013%

    No Known Activations