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

    Neuronpedia

    INDEX
    Explanations

    clear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	bus
    -0.07
     weakSelf
    -0.07
     rehears
    -0.06
     charities
    -0.06
    neği
    -0.06
     Nh
    -0.06
    '></
    -0.06
     انقل
    -0.06
    '>".$
    -0.06
     kayıt
    -0.06
    POSITIVE LOGITS
    andre
    0.07
     phân
    0.06
    _Application
    0.06
    LIKE
    0.06
    PLY
    0.06
     선수
    0.06
     Funny
    0.06
    体系
    0.06
     simply
    0.06
    otions
    0.06
    Act Density 0.000%

    No Known Activations