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

    Neuronpedia

    INDEX
    Explanations

    continued

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ritual
    -0.08
     tratt
    -0.08
    .metadata
    -0.08
     mentality
    -0.07
     Marco
    -0.07
    正规的
    -0.07
     plein
    -0.07
    鼻
    -0.07
     Finest
    -0.07
     indoors
    -0.07
    POSITIVE LOGITS
    স্থা
    0.09
     surpre
    0.08
     dependent
    0.08
     tirar
    0.08
     bağlı
    0.08
    dependent
    0.08
    Dependent
    0.08
     sert
    0.08
     нашим
    0.08
     sikre
    0.07
    Act Density 0.086%

    No Known Activations