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

    Neuronpedia

    INDEX
    Explanations

    tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parade
    -0.07
    keyCode
    -0.07
    .salary
    -0.07
    parentId
    -0.06
    	grid
    -0.06
    -position
    -0.06
     Caucas
    -0.06
    Backup
    -0.06
     bigger
    -0.06
     للد
    -0.06
    POSITIVE LOGITS
    ButtonModule
    0.07
     elections
    0.06
     bought
    0.06
     broadband
    0.06
     توم
    0.06
     العربي
    0.06
     hmm
    0.05
     motivation
    0.05
    Towards
    0.05
    ковой
    0.05
    Act Density 0.106%

    No Known Activations