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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uintptr
    -0.58
     zove
    -0.52
    AccessorTable
    -0.50
     Most
    -0.49
    contentLoaded
    -0.48
    Most
    -0.48
    WebControls
    -0.47
    ريقة
    -0.46
    tagHelperRunner
    -0.45
     finnas
    -0.45
    POSITIVE LOGITS
     ourselves
    0.75
     related
    0.71
     broader
    0.66
     wider
    0.65
     society
    0.65
     SafeMath
    0.65
     larger
    0.63
     later
    0.59
    você
    0.59
     themſelves
    0.58
    Act Density 0.002%

    No Known Activations