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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knitting
    -0.08
     interpretation
    -0.08
     costo
    -0.07
     clue
    -0.07
     проч
    -0.07
    ();//
    -0.07
     Subway
    -0.07
     stair
    -0.07
     stitch
    -0.06
    ану
    -0.06
    POSITIVE LOGITS
    シ
    0.07
    .flink
    0.06
    ublish
    0.06
    .require
    0.06
     outings
    0.06
    aret
    0.06
    งเศ
    0.06
     pubkey
    0.06
     Singular
    0.06
    edik
    0.06
    Act Density 0.021%

    No Known Activations