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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'D
    -0.08
     terrorism
    -0.07
    ado
    -0.07
     verv
    -0.07
    Fr
    -0.07
    ﻀ
    -0.07
    .R
    -0.07
     Coronavirus
    -0.07
    矿泉水
    -0.06
    _construct
    -0.06
    POSITIVE LOGITS
    赎回
    0.08
     gateway
    0.07
    ."</
    0.07
    /run
    0.07
    .logs
    0.07
    ؍
    0.07
    аб
    0.07
    ἔ
    0.06
     imagePath
    0.06
    Ϋ
    0.06
    Act Density 0.010%

    No Known Activations