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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PTION
    -0.07
    esse
    -0.07
    	target
    -0.07
     withString
    -0.07
    -dialog
    -0.07
    нез
    -0.07
    etic
    -0.07
    redo
    -0.06
    Tensor
    -0.06
    еся
    -0.06
    POSITIVE LOGITS
     любой
    0.07
     noss
    0.06
     جديد
    0.06
     Bien
    0.06
     phy
    0.06
    _cu
    0.06
    Salir
    0.06
     поврежд
    0.06
     pocit
    0.06
    Chuck
    0.05
    Act Density 0.031%

    No Known Activations