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

    Neuronpedia

    INDEX
    Explanations

    equal signs in code

    oai_token-act-pair · gemini-2.0-flash

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.62
     https
    -0.51
     Pop
    -0.49
    fastjson
    -0.46
     Bit
    -0.45
     batch
    -0.45
    spro
    -0.45
     ferons
    -0.44
     http
    -0.44
    lá
    -0.43
    POSITIVE LOGITS
     propOrder
    0.65
     ***!
    0.63
    ագրություններ
    0.63
    AccessorTable
    0.60
     صوتيه
    0.59
    ISupport
    0.57
     inol
    0.57
     unfortunately
    0.56
    usercontent
    0.54
     Scip
    0.54
    Act Density 0.103%

    No Known Activations