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

    Neuronpedia

    INDEX
    Explanations

    technical/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    かり
    -0.08
     heuristic
    -0.07
    เภ
    -0.07
     ceremony
    -0.06
    ideal
    -0.06
     youngster
    -0.06
     goodies
    -0.06
    १�
    -0.06
     بشر
    -0.06
    mdir
    -0.06
    POSITIVE LOGITS
     الأ
    0.07
     Medic
    0.06
     clo
    0.06
    SCP
    0.06
     Λα
    0.06
     erotique
    0.06
     ++
    0.06
     sve
    0.06
    ras
    0.06
     SDL
    0.06
    Act Density 0.203%

    No Known Activations