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

    Neuronpedia

    INDEX
    Explanations

    novels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JoinColumn
    -0.07
     Bu
    -0.07
     reinforcements
    -0.07
    ıyla
    -0.07
    Anderson
    -0.07
    욛
    -0.07
     February
    -0.07
    	manager
    -0.07
    	Debug
    -0.07
     colore
    -0.06
    POSITIVE LOGITS
    勤
    0.07
    餐
    0.07
     chào
    0.07
    致电
    0.07
    砝
    0.06
    家纺
    0.06
    _waiting
    0.06
    SR
    0.06
     Right
    0.06
     çalış
    0.06
    Act Density 0.015%

    No Known Activations