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

    Neuronpedia

    INDEX
    Explanations

    Love like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ประมาณ
    -0.08
     Ө
    -0.08
     hoge
    -0.07
    仔
    -0.07
     препят
    -0.07
    ੰਗ
    -0.07
    TEXT
    -0.07
    สูง
    -0.07
     Texte
    -0.07
     writing
    -0.07
    POSITIVE LOGITS
     audiences
    0.12
    大众
    0.12
     востреб
    0.10
     большин
    0.09
     аудит
    0.09
     internautes
    0.09
     popularity
    0.09
    群众
    0.09
     masyarakat
    0.09
     personalities
    0.09
    Act Density 0.090%

    No Known Activations