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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esát
    -0.06
    ості
    -0.06
     saves
    -0.06
    af
    -0.06
    iger
    -0.06
     preventive
    -0.06
    iker
    -0.06
    	Size
    -0.06
     bright
    -0.06
    이버
    -0.06
    POSITIVE LOGITS
    otřeb
    0.07
     Telerik
    0.07
    .On
    0.07
     вопрос
    0.06
    _ss
    0.06
    انگلیسی
    0.06
    Spawn
    0.06
    -par
    0.06
    @admin
    0.06
    unteers
    0.06
    Act Density 0.051%

    No Known Activations