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

    Neuronpedia

    INDEX
    Explanations

    Text HOME to 741741

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒆝
    1.11
    ࢯ
    1.10
    𒑜
    1.10
    𒑘
    1.10
    𒍌
    1.10
    trrecl
    1.10
    FBSDKMacros
    1.10
    blockidcoin
    1.09
    𒆡
    1.09
    𒐹
    1.09
    POSITIVE LOGITS
     so
    0.64
    .
    0.63
     (
    0.62
     bad
    0.56
    ,
    0.55
    0.54
     un
    0.54
     prest
    0.54
     *
    0.51
     too
    0.50
    Act Density 0.034%

    No Known Activations