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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     virgin
    -0.08
    	entity
    -0.07
    -0.07
    _Interface
    -0.07
    -0.07
     appearing
    -0.07
    -0.07
    tí
    -0.07
     přech
    -0.06
     Μαρ
    -0.06
    POSITIVE LOGITS
    ->
    0.09
    -int
    0.07
    รว
    0.07
     �
    0.07
    мов
    0.06
    відом
    0.06
    дать
    0.06
    λος
    0.06
    �
    0.06
    -
    0.06
    Act Density 0.018%

    No Known Activations