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

    Neuronpedia

    INDEX
    Explanations

    Monday

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    觉醒
    -0.07
     Killer
    -0.07
     jumping
    -0.07
    Compilation
    -0.06
    Compiler
    -0.06
    网贷
    -0.06
    (spell
    -0.06
     essa
    -0.06
     roaming
    -0.06
     connectivity
    -0.06
    POSITIVE LOGITS
     Monday
    0.09
     האחרונות
    0.08
    ביניהם
    0.07
    𝑩
    0.07
     الغذ
    0.07
     الطل
    0.07
    )"
    0.07
    獄
    0.07
    bai
    0.07
    ⽉
    0.07
    Act Density 0.010%

    No Known Activations