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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thẳng
    -0.07
     thừa
    -0.07
     است
    -0.07
     알려
    -0.07
    模样
    -0.07
    윱
    -0.07
     resumed
    -0.06
    贷款
    -0.06
    roring
    -0.06
     learnt
    -0.06
    POSITIVE LOGITS
    び
    0.07
    𝔰
    0.07
    rections
    0.07
    ichten
    0.07
    ḳ
    0.07
    bib
    0.07
    appe
    0.07
    煙
    0.07
    ventions
    0.07
    vig
    0.06
    Act Density 0.050%

    No Known Activations