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
    noun
    -0.06
    kest
    -0.06
     coronavirus
    -0.06
    قه
    -0.06
    Egypt
    -0.06
    -bold
    -0.06
    }
↵
↵
    -0.06
     erroneous
    -0.06
     DSL
    -0.06
    $status
    -0.06
    POSITIVE LOGITS
     realistically
    0.06
    exels
    0.06
     inheritance
    0.06
    lle
    0.06
    .LinearLayout
    0.06
     innoc
    0.06
     OVERRIDE
    0.06
    startsWith
    0.06
     assumptions
    0.06
     teardown
    0.06
    Act Density 0.118%

    No Known Activations