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

    Neuronpedia

    INDEX
    Explanations

    et

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᒃ
    -0.09
    낙
    -0.08
    .dat
    -0.07
     תת
    -0.07
     moderators
    -0.07
    mod
    -0.07
     consultant
    -0.07
    ;\↵
    -0.07
    _PLAN
    -0.07
    .batch
    -0.07
    POSITIVE LOGITS
    𝗲
    0.07
     unequiv
    0.07
    交通
    0.07
     tess
    0.07
    0.06
    ｏ
    0.06
     muzzle
    0.06
    English
    0.06
    信息技术
    0.06
     addition
    0.06
    Act Density 0.009%

    No Known Activations